METHOD FOR TRAINING AND METHOD FOR TESTING DEEP LEARNING-BASED BEHAVIOR DETECTION MODEL THAT DETECTS BEHAVIOR OF PERSON THROUGH VIDEO ANALYSIS, AND TRAINING DEVICE AND TESTING DEVICE USING SAME
The present invention relates to a method for training a deep learning-based behavior detection model that detects the behavior of a person through video analysis, comprising steps in which a training device: (a) generates at least one first bounding box for training to at least one t-th bounding box for training, and at least one first skeleton keypoint for training to at least one t-th skeleton keypoint for training; (b) performs (i) a process of detecting a first discrete action for training to a t-th discrete action for training and (ii) a process of detecting a continuous action for training; and (c) generates at least one first loss with reference to each of the first discrete action for training to the t-th discrete action for training and each discrete action ground truth corresponding thereto, generates at least one second loss with reference to the continuous action for training and a continuous action ground truth corresponding thereto, and trains a discrete action detection network and a continuous action detection network by using the first loss and the second loss.
The present invention performs tasks by using an image analysis deep learning model on an image from at least one camera photographing a specific space of an offline market, vectorizes image analysis state information obtained by referring to task results and text analysis state information including at least a portion of POS data and POG data and stores same in a vector database, and acquires at least a portion of the image analysis state information and the text analysis state information corresponding to a first text command to an n-th text command for performing a natural language command related to management of the offline market through an LLM as the first state information to the n-th state information from the vector database to generate response information corresponding to the natural language command.
METHOD FOR TRAINING OBJECT DETECTOR FOR PREDICTING CENTER OF GRAVITY OF OBJECT PROJECTED ON GROUND, METHOD FOR USING TRAINED OBJECT DETECTOR TO IDENTIFY SAME OBJECT IN SPECIFIC SPACE FILMED BY PLURALITY OF CAMERAS HAVING DIFFERENT VIEWING FRUSTUMS, AND TRAINING DEVICE AND OBJECT-IDENTIFYING DEVICE WHICH USE METHODS
The present invention relates to a method for training an object detector for predicting the center of gravity of an object projected on the ground, the method comprising the steps in which: (a) a training device acquires one or more training images from a training dataset; (b) the training device inputs each of the training images to an object detector, so that the object detector performs object detection on each of the training images and generates object detection results, including information on a predicted bounding box corresponding to at least one region of interest (ROI) in which at least one object is predicted to be located in each of the training images and information on a predicted projection point at which the center of gravity of each object is projected on the ground; and (c) the training device uses each of object detection losses, generated by referring to each of the object detection results and each piece of ground truth information corresponding to each of the training images, so as to train the object detector.
G06V 10/762 - Arrangements for image or video recognition or understanding using pattern recognition or machine learning using clustering, e.g. of similar faces in social networks
G06T 3/00 - Geometric image transformations in the plane of the image
4.
LEARNING METHOD AND LEARNING DEVICE FOR TRAINING MULTI-TASKING NETWORK THAT PERFORMS MULTI-TASKS BY USING DATASETS HAVING DIFFERENT TASK LABELS AND TESTING METHOD AND TESTING DEVICE USING THE SAME
There is provided a method for training a multi-tasking network performing multi-tasks by using datasets having different task labels. In response to acquiring specific training data from main dataset including 1-st sub dataset having 1-st task label to n-th sub dataset having n-th task label, a learning device inputs the specific training data into a 1-st multi-tasking network to an n-th multi-tasking network, to thereby instruct the 1-st multi-tasking network to the n-th multi-tasking network to perform learning operation on the specific training data and to output n task results; calculates a 1-st task loss to an n-th task loss by referring to 1-st specific task result to n-th specific task result; calculates a 1-st unlabeled consistency loss group to an n-th unlabeled consistency loss group; and trains the 1-st multi-tasking network to the n-th multi-tasking network by using a total task loss and a total consistency loss.
LEARNING METHOD AND LEARNING APPARATUS FOR TRAINING DEEP LEARNING-BASED GAZE DETECTION MODEL FOR DETECTING GAZE, AND TEST METHOD AND TEST APPARATUS USING SAME
This method for training a deep learning-based gaze detection model comprises the steps of: (a) generating at least one body direction loss by using predicted body direction information and labeled body direction information included in first ground truth information corresponding to a first training image, and training a body FC layer and a body convolutional layer by using the body direction loss; and (b) inputting a first integrated feature map into a head FC layer so that the head FC layer outputs at least one piece of first predicted head direction information in which a direction, in which the front of the head of a second person faces, is predicted by performing FC calculation on the first integrated feature map at least once, generating at least one head direction loss by using the first predicted head direction information and labeled head direction information included in a second ground truth corresponding to a second training image, and training the head FC layer and a head convolutional layer by using the head direction loss.
G06V 10/774 - Generating sets of training patternsBootstrap methods, e.g. bagging or boosting
G06V 10/80 - Fusion, i.e. combining data from various sources at the sensor level, preprocessing level, feature extraction level or classification level
G06V 10/764 - Arrangements for image or video recognition or understanding using pattern recognition or machine learning using classification, e.g. of video objects
G06V 40/10 - Human or animal bodies, e.g. vehicle occupants or pedestriansBody parts, e.g. hands
G06V 40/16 - Human faces, e.g. facial parts, sketches or expressions
Method for training object detector capable of predicting center of mass of object projected onto ground, method for recognizing identical object in specific space captured from a plurality of cameras having different viewing frustums using trained object detector, and learning device and object recognizing device using the same
Method of training an object detector for predicting centers of mass of objects projected onto a ground is provided. The method includes steps of: acquiring training images from training data set; inputting each of training images into the object detector to thereby instruct the object detector to perform object detection for the training images and thus generate object detection results including (i) information on predicted bounding boxes, corresponding to one or more ROIs, acquired by predicting each of locations of the objects in the training images and (ii) information on predicted projection points acquired by projecting the centers of mass of the objects onto the ground; and training the object detector by using object detection losses generated by referring to the object detection results and information on ground truths corresponding to the training images.
G06T 7/70 - Determining position or orientation of objects or cameras
G06V 10/25 - Determination of region of interest [ROI] or a volume of interest [VOI]
G06V 10/764 - Arrangements for image or video recognition or understanding using pattern recognition or machine learning using classification, e.g. of video objects
G06V 10/762 - Arrangements for image or video recognition or understanding using pattern recognition or machine learning using clustering, e.g. of similar faces in social networks
7.
Method for training video object detection model using training dataset and learning device using the same
A method of training a video object detection model by using a training dataset is provided, including steps of: a learning device (a) after acquiring a training image (i) inputting the training image and first prior information, set as having probabilities of objects existing in locations in the training image, into the video object detection model, to thereby detect the objects and thus output first object detection information, and (ii) generating second prior information, which includes location information of the objects on the training image; (b) inputting the training image and the second prior information into the video object detection model, to detect the objects on the training and thus output second object detection information; and (c) generating a loss by referring to the second object detection information and a ground truth corresponding to the training image, and train the video object detection model to minimize the loss.
A method for de-identifying a privacy-related region within an image, including steps of: (a) inputting an input image into a segmentation network to apply a segmentation operation to the input image and generate at least part of (i) each of region probabilities of each of the pixels being estimated as the privacy-related region and (ii) each of region sizes assigned to each of the pixels of the input image; and (b) (i) calculating each of standard deviations for each of the pixels of the input image by using at least part of each of the region probabilities and each of the region sizes, thereby generating each of region standard deviations and (ii) applying a de-identifying operation to each of the pixels of the input image by using each of the region standard deviations, to thereby de-identify the privacy-related region within the input image.
A method for de-identifying a privacy-related region within an image, including steps of: (a) inputting an input image into a segmentation network to apply a segmentation operation to the input image and generate at least part of (i) each of region probabilities of each of the pixels being estimated as the privacy-related region and (ii) each of region sizes assigned to each of the pixels of the input image; and (b) (i) calculating each of standard deviations for each of the pixels of the input image by using at least part of each of the region probabilities and each of the region sizes, thereby generating each of region standard deviations and (ii) applying a de-identifying operation to each of the pixels of the input image by using each of the region standard deviations, to thereby de-identify the privacy-related region within the input image.
G06T 3/40 - Scaling of whole images or parts thereof, e.g. expanding or contracting
10.
LEARNING METHOD AND LEARNING DEVICE FOR TRAINING OBFUSCATION NETWORK CAPABLE OF OBFUSCATING ORIGINAL DATA FOR PRIVACY TO ACHIEVE INFORMATION RESTRICTION OBFUSCATION AND TESTING METHOD AND TESTING DEVICE USING THE SAME
A learning method for training an obfuscation network, including steps of: (a) inputting a training data into the obfuscation network to (i) extract features and thus generate a data representation by performing a learning operation on the training data and (ii) transform the data representation and thus generate an anonymized data representation, and (b) inputting the anonymized data representation into a task learning network to (i) perform a task by using the anonymized data representation and thus output a task result, (ii) generate a task loss by referring to the task result and its corresponding ground truth, (iii) train the task learning network through a first backpropagation of the task loss such that the task loss is minimized, and (iv) train the obfuscation network through a second backpropagation of the task loss such that the task loss is minimized.
Learning method and learning device for training obfuscation network capable of obfuscating original data for privacy and testing method and testing device using the same
A learning method for training an obfuscation network capable of obfuscating original data for privacy, including steps of: (a) inputting training data into the obfuscation network to filter frequency information of the training data and thus generate obfuscated data; and (b) (i) inputting the obfuscated data into a learning network to generate characteristic information by performing learning operation on the obfuscated data, (ii) generating at least one task loss by referring to (ii-1) the characteristic information and its corresponding ground truth or (ii-2) a task-specific output, generated by using the characteristic information, and its corresponding ground truth, and (iii) training at least one of the learning network and the obfuscation network through a backpropagation of the task loss.
A training image to be used in training a learning network is generated. The method of generating the training image includes steps of: (a) a labeling device, in response to acquiring an original image, (i) inputting the original image into an image recognition network to detect privacy-related regions from the original image, (ii) adding dummy regions, different from the detected privacy-related regions, onto the original image, and (iii) setting the privacy-related regions and the dummy regions as obfuscation-expected regions which represent regions to be obfuscated in the original image; (b) the labeling device generating an obfuscated image by obfuscating the obfuscation-expected regions; and (c) the labeling device labeling the obfuscated image to be corresponding to a task of the learning network to be trained, to thereby generate the training image to be used in training the learning network.
LEARNING METHOD AND LEARNING DEVICE FOR TRAINING OBFUSCATION NETWORK CAPABLE OF OBFUSCATING ORIGINAL DATA FOR PRIVACY AND TESTING METHOD AND TESTING DEVICE USING THE SAME
A learning method for training an obfuscation network capable of obfuscating original data for privacy, including steps of: (a) inputting training data into the obfuscation network to filter frequency information of the training data and thus generate obfuscated data; and (b) (i) inputting the obfuscated data into a learning network to generate characteristic information by performing learning operation on the obfuscated data, (ii) generating at least one task loss by referring to (ii-1) the characteristic information and its corresponding ground truth or (ii-2) a task-specific output, generated by using the characteristic information, and its corresponding ground truth, and (iii) training at least one of the learning network and the obfuscation network through a backpropagation of the task loss.
METHOD FOR TRAINING AND TESTING OBFUSCATION NETWORK CAPABLE OF OBFUSCATING DATA TO PROTECT PERSONAL INFORMATION, AND LEARNING DEVICE AND TESTING DEVICE USING THE SAME
A method for training an obfuscation network is provided. The method includes steps of: a learning device (a) inputting training data into an obfuscation network to generate obfuscated data for training; (b) (i) inputting the obfuscated data for training into a discriminator to output a current obfuscation score for training and (ii) (ii-1) inputting first sub-data for training into a learning network to output first sub characteristic information for training and updating current updated learning parameters of the learning network to first sub updated learning parameters and (ii-2) while increasing an integer k from 2 to n, inputting k-th sub-data for training into the learning network to output k-th sub characteristic information for training and updating (k-1)-th sub updated learning parameters of the learning network to k-th sub updated learning parameters; and (c) updating previous updated obfuscation parameters of the obfuscation network to current updated obfuscation parameters.
A method for tracking one or more objects in a specific space is provided. The method includes steps of: (a) inputting original images of the specific space taken from camera to an obfuscation network and instructing the obfuscation network to obfuscate the original images to generate obfuscated images such that the obfuscated images are not identifiable as the original images by a human but the obfuscated images are identifiable as the original images by a learning network; (b) inputting the obfuscated images into the learning network, and instructing the learning network to detect obfuscated target objects, corresponding to target objects to be tracked, in the obfuscated images, to thereby output information on the obfuscated target objects; and (c) tracking the obfuscated target objects in the specific space by referring to the information on the obfuscated target objects.
A method for training a homography attention module (HAM) to perform multi-view object detection includes steps of: generating, from an i-th feature map corresponding to each of multiple training images representing multi-views of a target space, a 1-st to a d-th channel attention map for determining channel attention scores each channel included in the i-th feature map has for each of a 1-st to a d-th height plane of the target space, generating a 1-st to a d-th channel refined feature map by referring to channels with top k channel attention scores for each height, element-wisely multiplying them with corresponding spatial attention map generated therefrom to produce a 1-st to a d-th spatial refined feature map, and then homographically transforming them onto corresponding height plane and aggregating them to generate a BEV occupancy heatmap, which is used with its GT for training.
G06V 10/82 - Arrangements for image or video recognition or understanding using pattern recognition or machine learning using neural networks
G06V 10/77 - Processing image or video features in feature spacesArrangements for image or video recognition or understanding using pattern recognition or machine learning using data integration or data reduction, e.g. principal component analysis [PCA] or independent component analysis [ICA] or self-organising maps [SOM]Blind source separation
G06V 10/771 - Feature selection, e.g. selecting representative features from a multi-dimensional feature space
17.
Method for generating obfuscated image to be used in training learning net work and labeling device using the same
A training image to be used in training a learning network is generated. The method of generating the training image includes steps of: (a) a labeling device, in response to acquiring an original image, (i) inputting the original image into an image recognition network to detect privacy-related regions from the original image, (ii) adding dummy regions, different from the detected privacy-related regions, onto the original image, and (iii) setting the privacy-related regions and the dummy regions as obfuscation-expected regions which represent regions to be obfuscated in the original image; (b) the labeling device generating an obfuscated image by obfuscating the obfuscation-expected regions; and (c) the labeling device labeling the obfuscated image to be corresponding to a task of the learning network to be trained, to thereby generate the training image to be used in training the learning network.
A method for tracking one or more objects in a specific space is provided. The method includes steps of: (a) inputting original images of the specific space taken from camera to an obfuscation network and instructing the obfuscation network to obfuscate the original images to generate obfuscated images such that the obfuscated images are not identifiable as the original images by a human but the obfuscated images are identifiable as the original images by a learning network; (b) inputting the obfuscated images into the learning network, and instructing the learning network to detect obfuscated target objects, corresponding to target objects to be tracked, in the obfuscated images, to thereby output information on the obfuscated target objects; and (c) tracking the obfuscated target objects in the specific space by referring to the information on the obfuscated target objects.
H04N 5/232 - Devices for controlling television cameras, e.g. remote control
G06T 7/254 - Analysis of motion involving subtraction of images
19.
Method for training and testing obfuscation network capable of obfuscating data to protect personal information, and learning device and testing device using the same
A method for training an obfuscation network is provided. The method includes steps of: a learning device (a) inputting training data into an obfuscation network to generate obfuscated data for training; (b) (i) inputting the obfuscated data for training into a discriminator to output a current obfuscation score for training and (ii) (ii-1) inputting first sub-data for training into a learning network to output first sub characteristic information for training and updating current updated learning parameters of the learning network to first sub updated learning parameters and (ii-2) while increasing an integer k from 2 to n, inputting k-th sub-data for training into the learning network to output k-th sub characteristic information for training and updating (k−1)-th sub updated learning parameters of the learning network to k-th sub updated learning parameters; and (c) updating previous updated obfuscation parameters of the obfuscation network to current updated obfuscation parameters.
A method for producing a labeled image is provided. The method includes steps of: a labeling server (i) providing an image modifying interface to a user device to generate at least one anonymized image by anonymizing the original image except a specific labeling region among at least one labeling region, or generate at least one cropped image by cropping the labeling region, thus generating at least one transformed image by applying at least one transform function to the anonymized image or the cropped image, (ii) acquiring an obfuscated image by obfuscating the original image, (iii) acquiring at least one partial labeled image by allowing labelers to label the transformed image, and (iv) inversely applying the transform function received from the user device to the partial labeled image, thus generating at least one piece of adjusted partial labeling information and combining thereof with the obfuscated image to generate the labeled image.
A method of training an obfuscation network for obfuscating original data to protect personal information is provided. The method includes steps of: a learning device, (a) inputting acquired training data into an obfuscation network to obfuscate the training data and inputting the obfuscated training data into an augmentation network to augment the obfuscated training data; (b) (i) inputting the augmented obfuscated training data into a learning network to generate first characteristic information and (ii) inputting the training data into the learning network to generate second characteristic information; and (c) training the obfuscation network such that (i) a first error, calculated by using the first and the second characteristic information, is minimized and (ii) a second error, calculated by using (ii-1) modified training data or modified obfuscated training data, and (ii-2) the obfuscated training data or the augmented obfuscated training data, is maximized.
METHOD FOR TRAINING AND TESTING OBFUSCATION NETWORK CAPABLE OF PROCESSING DATA TO BE OBFUSCATED FOR PRIVACY, AND TRAINING DEVICE AND TESTING DEVICE USING THE SAME
A method for training an obfuscation network for obfuscating data is provided. The method includes steps of: a learning device (a) (i) inputting training data into an obfuscation network to obfuscate the training data and generate obfuscated training data, and (ii) inputting the obfuscated training data into a compression network to generate binary training data and generate compression adaptive obfuscated training data; (b) inputting the compression adaptive obfuscated training data into a learning network to apply learning operation and generate first characteristic information and inputting the training data into the learning network to generate second characteristic information and (c) training the obfuscation network such that first errors, calculated using the first and the second characteristic information, are minimized and such that second errors, calculated using (1) modified training data or modified obfuscated training data and (2) the obfuscated training data or the compression adaptive obfuscated training data, are maximized.
METHOD FOR TRAINING AND TESTING USER LEARNING NETWORK TO BE USED FOR RECOGNIZING OBFUSCATED DATA CREATED BY OBFUSCATING ORIGINAL DATA TO PROTECT PERSONAL INFORMATION AND USER LEARNING DEVICE AND TESTING DEVICE USING THE SAME
A method for training a user learning network for recognizing obfuscated data is provided. The method includes steps of: a learning device (a) (i) inputting obfuscated data, from a data provider, into a user learning network to generate first characteristic information and (ii) updating parameters of a user task layer and a first user batch normalizing layer such that an error, calculated using (1) the first characteristic information or a first task specific output and (2) a first ground truth of the obfuscated data, is minimized, and (b) (i) inputting original data, from a user, into the user learning network to generate second characteristic information and (ii) updating parameters of the user task layer and the second user batch normalizing layer such that an error, calculated using (1) the second characteristic information or a second task specific output and (2) a second ground truth of the original data, is minimized.
Methods for training universal discriminator capable of determining degrees of de-identification for images and obfuscation network capable of obfuscating images and training devices using the same
Methods for training a universal discriminator and an obfuscation network are provided. The methods include steps of: generating an obfuscated image by obfuscating an original image through the obfuscation network, characteristic information by applying learning operation to the obfuscated image through a surrogate network, a first discriminant score determining a degree of de-identification for the obfuscated image through the universal discriminator, and a second discriminant score determining whether the obfuscated image is real or fake through a regular discriminator, and thus training the obfuscation network through minimizing an accuracy loss of the surrogate network, and maximizing the first and second discriminant scores, wherein the universal discriminator has been trained by classifying de-identified images into positive or negative samples according to degrees of de-identification, generating discriminant scores determining degrees of de-identification for the samples through the universal discriminator, and training the universal discriminator by minimizing discriminator losses of the discriminant scores.
G06K 9/62 - Methods or arrangements for recognition using electronic means
G06N 3/04 - Architecture, e.g. interconnection topology
G06K 9/00 - Methods or arrangements for reading or recognising printed or written characters or for recognising patterns, e.g. fingerprints
25.
METHODS FOR TRAINING AND TESTING OBFUSCATION NETWORK CAPABLE OF PERFORMING DISTINCT CONCEALING PROCESSES FOR DISTINCT REGIONS OF ORIGINAL IMAGE AND LEARNING AND TESTING DEVICES USING THE SAME
A method for training an obfuscation network capable of performing distinct concealing processes for distinct regions of an original image is provided. The method includes steps of: a learning device (a) inputting a training image into the obfuscation network to generate an obfuscated training image by performing a 1-st to an n-th concealing process respectively on a 1-st to an n-th training region of the training image; (b) inputting the obfuscated training image into a 1-st to an n-th discriminator to respectively generate a 1-st to an n-th obfuscated image score on determining whether the obfuscated training image is real or fake, and inputting the obfuscated training image into an image recognition network to apply learning operation on the obfuscated training image to generate feature information for training; and (c) training the obfuscation network such that an accumulated loss is maximized, and an accuracy loss is minimized.
G06T 3/00 - Geometric image transformations in the plane of the image
G06T 5/50 - Image enhancement or restoration using two or more images, e.g. averaging or subtraction
G06T 3/40 - Scaling of whole images or parts thereof, e.g. expanding or contracting
G06F 21/62 - Protecting access to data via a platform, e.g. using keys or access control rules
26.
Method for training and testing user learning network to be used for recognizing obfuscated data created by obfuscating original data to protect personal information and user learning device and testing device using the same
A method for training a user learning network for recognizing obfuscated data is provided. The method includes steps of: a learning device (a) (i) inputting obfuscated data, from a data provider, into a user learning network to generate first characteristic information and (ii) updating parameters of a user task layer and a first user batch normalizing layer such that an error, calculated using (1) the first characteristic information or a first task specific output and (2) a first ground truth of the obfuscated data, is minimized, and (b) (i) inputting original data, from a user, into the user learning network to generate second characteristic information and (ii) updating parameters of the user task layer and the second user batch normalizing layer such that an error, calculated using (1) the second characteristic information or a second task specific output and (2) a second ground truth of the original data, is minimized.
G06F 21/62 - Protecting access to data via a platform, e.g. using keys or access control rules
G06K 9/62 - Methods or arrangements for recognition using electronic means
27.
METHOD FOR TRAINING OBFUSCATION NETWORK WHICH CONCEALS ORIGINAL DATA TO BE USED FOR MACHINE LEARNING AND TRAINING SURROGATE NETWORK WHICH USES OBFUSCATED DATA GENERATED BY OBFUSCATION NETWORK AND LEARNING DEVICE USING THE SAME AND METHOD FOR TESTING TRAINED OBFUSCATION NETWORK AND TESTING DEVICE USING THE SAME
A method of a master learning device to train obfuscation networks and surrogate networks is provided. The method includes steps of: a master learning device (a) acquiring obfuscated data and ground truths from learning devices corresponding to owners or delegates of the original data and their ground truths; (b) (i) inputting the obfuscated data into a surrogate network, to apply learning operation thereto and generate characteristic information, (ii) calculating losses using the ground truths and the characteristic information or its task specific output, and (iii) training the surrogate network such that the losses or their average is minimized; and (c) transmitting the losses to the learning devices, to train the obfuscation networks such that the losses are minimized and that other losses calculated using the original data and the obfuscated data are maximized, and transmit network gradients of the trained obfuscation networks to the master learning device for its update.
G06F 21/14 - Protecting executable software against software analysis or reverse engineering, e.g. by obfuscation
28.
METHOD FOR TRAINING OBFUSCATION NETWORK WHICH CONCEALS ORIGINAL DATA TO BE USED FOR MACHINE LEARNING AND TRAINING SURROGATE NETWORK WHICH USES OBFUSCATED DATA GENERATED BY OBFUSCATION NETWORK AND METHOD FOR TESTING TRAINED OBFUSCATION NETWORK AND LEARNING DEVICE AND TESTING DEVICE USING THE SAME
A method for training an obfuscation network and a surrogate network is provided. The method includes steps of: a 1-st learning device (a) inputting original data of a 1-st party, corresponding thereto, into the obfuscation network to generate obfuscated data wherein the 1-st party owns the original data or is an entity to whom the original data is relegated; (b) transmitting the obfuscated data and the ground truth to a 2-nd learning device corresponding to a 2-nd party, and instructing the 2-nd learning device to (i) input the obfuscated data into the surrogate network to generate characteristic information, (ii) calculate 1-st losses using the ground truth and one of the characteristic information and task specific outputs, and (iii) train the surrogate network minimizing the 1-st losses, and transmit the 1-st losses to the 1-st learning device; and (c) training the obfuscation network minimizing the 1-st losses and maximizing 2-nd losses.
G06F 21/14 - Protecting executable software against software analysis or reverse engineering, e.g. by obfuscation
29.
Method for training and testing obfuscation network capable of processing data to be obfuscated for privacy, and training device and testing device using the same
A method for training an obfuscation network for obfuscating data is provided. The method includes steps of: a learning device (a) (i) inputting training data into an obfuscation network to obfuscate the training data and generate obfuscated training data, and (ii) inputting the obfuscated training data into a compression network to generate binary training data and generate compression adaptive obfuscated training data; (b) inputting the compression adaptive obfuscated training data into a learning network to apply learning operation and generate first characteristic information and inputting the training data into the learning network to generate second characteristic information and (c) training the obfuscation network such that first errors, calculated using the first and the second characteristic information, are minimized and such that second errors, calculated using (1) modified training data or modified obfuscated training data and (2) the obfuscated training data or the compression adaptive obfuscated training data, are maximized.
A method of training an obfuscation network for obfuscating original data to protect personal information is provided. The method includes steps of a learning device, (a) inputting acquired training data into an obfuscation network to obfuscate the training data and inputting the obfuscated training data into an augmentation network to augment the obfuscated training data; (b) (i) inputting the augmented obfuscated training data into a learning network to generate first characteristic information and (ii) inputting the training data into the learning network to generate second characteristic information; and (c) training the obfuscation network such that (i) a first error, calculated by using the first and the second characteristic information, is minimized and (ii) a second error, calculated by using (ii-1) modified training data or modified obfuscated training data, and (ii-2) the obfuscated training data or the augmented obfuscated training data, is maximized.
A method for producing a labeled image is provided. The method includes steps of: a labeling server (i) providing an image modifying interface to a user device to generate at least one anonymized image by anonymizing the original image except a specific labeling region among at least one labeling region, or generate at least one cropped image by cropping the labeling region, thus generating at least one transformed image by applying at least one transform function to the anonymized image or the cropped image, (ii) acquiring an obfuscated image by obfuscating the original image, (iii) acquiring at least one partial labeled image by allowing labelers to label the transformed image, and (iv) inversely applying the transform function received from the user device to the partial labeled image, thus generating at least one piece of adjusted partial labeling information and combining thereof with the obfuscated image to generate the labeled image.
A method for preventing breach of original data for deep learning is provided. The method includes steps of: a data breach preventing device (a) adding noise onto the acquired original data to generate 1-st noisy data; and (b)(b1) while increasing an integer k from 1 to an integer larger than 0, (i) inputting k-th noisy data into a learning network, to apply learning operations to the k-th noisy data using learned parameters of the learning network, and to output k-th characteristic information, and (ii) launching an adversarial attack on the k-th noisy data via backpropagation using at least one of (ii-1) (k_1)-st losses calculated using the k-th characteristic information and a 1-st ground truth, and (ii-2) (k_2)-nd losses calculated using (1) a k-th task specific output and (2) a 2-nd ground truth, and generating (k+1)-th noisy data, and (b2) as a result, generating n-th noisy data as watermarked data.
G06N 20/10 - Machine learning using kernel methods, e.g. support vector machines [SVM]
33.
Methods for training and testing obfuscation network capable of performing distinct concealing processes for distinct regions of original image and learning and testing devices using the same
A method for training an obfuscation network capable of performing distinct concealing processes for distinct regions of an original image is provided. The method includes steps of: a learning device (a) inputting a training image into the obfuscation network to generate an obfuscated training image by performing a 1-st to an n-th concealing process respectively on a 1-st to an n-th training region of the training image; (b) inputting the obfuscated training image into a 1-st to an n-th discriminator to respectively generate a 1-st to an n-th obfuscated image score on determining whether the obfuscated training image is real or fake, and inputting the obfuscated training image into an image recognition network to apply learning operation on the obfuscated training image to generate feature information for training; and (c) training the obfuscation network such that an accumulated loss is maximized, and an accuracy loss is minimized.
Method for training obfuscation network which conceals original data to be used for machine learning and training surrogate network which uses obfuscated data generated by obfuscation network and learning device using the same and method for testing trained obfuscation network and testing device using the same
A method of a master learning device to train obfuscation networks and surrogate networks is provided. The method includes steps of: a master learning device (a) acquiring obfuscated data and ground truths from learning devices corresponding to owners or delegates of the original data and their ground truths; (b) (i) inputting the obfuscated data into a surrogate network, to apply learning operation thereto and generate characteristic information, (ii) calculating losses using the ground truths and the characteristic information or its task specific output, and (iii) training the surrogate network such that the losses or their average is minimized; and (c) transmitting the losses to the learning devices, to train the obfuscation networks such that the losses are minimized and that other losses calculated using the original data and the obfuscated data are maximized, and transmit network gradients of the trained obfuscation networks to the master learning device for its update.
Method for training obfuscation network which conceals original data to be used for machine learning and training surrogate network which uses obfuscated data generated by obfuscation network and method for testing trained obfuscation network and learning device and testing device using the same
A method for training an obfuscation network and a surrogate network is provided. The method includes steps of: a 1st learning device (a) inputting original data of a 1st party, corresponding thereto, into the obfuscation network to generate obfuscated data wherein the 1st party owns the original data or is an entity to whom the original data is delegated; (b) transmitting the obfuscated data and the ground truth to a 2nd learning device corresponding to a 2nd party, and instructing the 2nd learning device to (i) input the obfuscated data into the surrogate network to generate characteristic information, (ii) calculate 1st losses using the ground truth and one of the characteristic information and task specific outputs, and (iii) train the surrogate network minimizing the 1st losses, and transmit the 1st losses to the 1st learning device; and (c) training the obfuscation network minimizing the 1st losses and maximizing 2nd losses.
METHOD FOR TRAINING AND TESTING ADAPTION NETWORK CORRESPONDING TO OBFUSCATION NETWORK CAPABLE OF PROCESSING DATA TO BE CONCEALED FOR PRIVACY, AND TRAINING DEVICE AND TESTING DEVICE USING THE SAME
A method for learning an adaption network corresponding to an obfuscation network used for concealing original data is provided. The method includes steps of: (a) on condition that a 1-st learning device has performed or is performing processes of (i) instructing the obfuscation network to obfuscate the training data to generate obfuscated training data, (ii) inputting the obfuscated training data into a learning network to generate 1-st characteristic information for training and inputting the training data into the learning network to generate 2-nd characteristic information for training, and (iii) learning the obfuscation network, a 2-nd learning device performing one of inputting the training data into the adaption network to generate 1-st feature adapted data and inputting test data into the adaption network to generate 2-nd feature adapted data and one of (i) acquiring a 1-st adaption ground truth and learning the adaption network and (ii) learning the adaption network.
G06N 20/10 - Machine learning using kernel methods, e.g. support vector machines [SVM]
G06F 21/62 - Protecting access to data via a platform, e.g. using keys or access control rules
37.
METHOD FOR LEARNING AND TESTING USER LEARNING NETWORK TO BE USED FOR RECOGNIZING OBFUSCATED DATA CREATED BY CONCEALING ORIGINAL DATA TO PROTECT PERSONAL INFORMATION AND LEARNING DEVICE AND TESTING DEVICE USING THE SAME
A method for learning a user learning network to recognize obfuscated data created by concealing original data is provided. The method includes steps of: a 2-nd learning device, (a) on condition that a 1-st learning device has performed (i) instructing the obfuscation network to generate obfuscated training data, (ii) inputting (ii-1) the obfuscated training data into, to generate 1-st characteristic information for training, and (ii-2) the training data, to generate 2-nd characteristic information for training, into a learning network for training and (iii) learning the obfuscation network, and acquiring (i) the obfuscated training data and a training data GT, or (ii) obfuscated test data and a test data GT; (b) inputting (i) the obfuscated training data, to generate 3-rd characteristic information for training, or (ii) the obfuscated test data, to generate 4-th characteristic information for training, into the user learning network; and (c) learning the user learning network.
A method for preventing breach of original data for deep learning is provided. The method includes steps of: a data breach preventing device (a) adding noise onto the acquired original data to generate 1-st noisy data; and (b)(b1) while increasing an integer k from 1 to an integer larger than 0, (i) inputting k-th noisy data into a learning network, to apply learning operations to the k-th noisy data using learned parameters of the learning network, and to output k-th characteristic information, and (ii) launching an adversarial attack on the k-th noisy data via backpropagation using at least one of (ii-1) (k_1)-st losses calculated using the k-th characteristic information and a 1-st ground truth, and (ii-2) (k_2)-nd losses calculated using (1) a k-th task specific output and (2) a 2-nd ground truth, and generating (k+1)-th noisy data, and (b2) as a result, generating n-th noisy data as watermarked data.
Compilation and systematization of information in databanks; on-line data processing services; electronic data processing services; collating of data in computer databases; computerised file management; compilation and systemization of information used in electronic transmissions; compilation of information into computer databases; computer database retrieval; computer database management; systematization of data in computer databases; systemisation of information into computer databases; collection and systematisation of information into computer databases; computerized data processing services; computer file management; Wholesale store services featuring electronic equipment with data recorded electronically; Wholesale store services featuring data file recorded electronically; Retail store services featuring electronic equipment with data recorded electronically; Retail store services featuring data file recorded electronically; Business intermediary services relating to the purchase and sale of data recorded electronically, namely, providing a website for connecting sellers with buyers relating to the purchase and sale of data recorded electronically; Wholesale store services featuring software; Retail store services featuring software; Business intermediary services relating to the purchase and sale of software, namely, providing a website for connecting sellers with buyers relating to the purchase and sale of software Providing access to electronic information, communication and transaction platforms on the Internet; providing access to platforms on the Internet, as well as on the mobile Internet; providing access to information on the internet; providing user access to platforms on the Internet; providing access to e-commerce platforms on the Internet; providing access to an online platform containing a collection of computer software; data transfer services, namely, transfer of data by telecommunication; transmission of information via national and international networks; providing electronic telecommunications connections to and between databases; communication services for the electronic transmission of data; information transmission via electronic communications networks; providing access to databases and information via global computer networks; transmission and distribution of data via a global computer network; transmission of data via a global computer network; data transmission services between networked computer systems; data streaming services; on-demand transmission services of data, audio, video, gaming and multimedia content; providing user access on computer programs in data networks; providing on-line user access to data on the Internet in the field of electronics; transfer of information and data by telecommunications via on-line services
40.
Method for concealing data and data obfuscation device using the same
A method for concealing original data to protect personal information is provided. The method includes steps of: a data obfuscation device (a) if the original data is acquired, inputting the original data or its modified data into a learning network, and allowing the learning network to (i) apply a network operation to the original data or the modified data using learned parameters of the learning network and thus to (ii) output characteristic information on the original data or the modified data; and (b) updating the original data or the modified data via backpropagation using part of (i) 1-st losses calculated by referring to the characteristic information and its corresponding 1-st ground truth, and (ii) 2-nd losses calculated by referring to (ii-1) a task specific output generated by using the characteristic information and (ii-2) a 2-nd ground truth corresponding to the task specific output, to thereby generate obfuscated data.
Method for learning and testing user learning network to be used for recognizing obfuscated data created by concealing original data to protect personal information and learning device and testing device using the same
A method for learning a user learning network to recognize obfuscated data created by concealing original data is provided. The method includes steps of: a 2-nd learning device, (a) on condition that a 1-st learning device has performed (i) instructing the obfuscation network to generate obfuscated training data, (ii) inputting (ii-1) the obfuscated training data into, to generate 1-st characteristic information for training, and (ii-2) the training data, to generate 2-nd characteristic information for training, into a learning network for training and (iii) learning the obfuscation network, and acquiring (i) the obfuscated training data and a training data GT, or (ii) obfuscated test data and a test data GT; (b) inputting (i) the obfuscated training data, to generate 3-rd characteristic information for training, or (ii) the obfuscated test data, to generate 4-th characteristic information for training, into the user learning network; and (c) learning the user learning network.
G06K 9/62 - Methods or arrangements for recognition using electronic means
G06F 21/14 - Protecting executable software against software analysis or reverse engineering, e.g. by obfuscation
42.
Method for training and testing adaption network corresponding to obfuscation network capable of processing data to be concealed for privacy, and training device and testing device using the same
A method for learning an adaption network corresponding to an obfuscation network used for concealing original data is provided. The method includes steps of: (a) on condition that a 1-st learning device has performed or is performing processes of (i) instructing the obfuscation network to obfuscate the training data to generate obfuscated training data, (ii) inputting the obfuscated training data into a learning network to generate 1-st characteristic information for training and inputting the training data into the learning network to generate 2-nd characteristic information for training, and (iii) learning the obfuscation network, a 2-nd learning device performing one of inputting the training data into the adaption network to generate 1-st feature adapted data and inputting test data into the adaption network to generate 2-nd feature adapted data and one of (i) acquiring a 1-st adaption ground truth and learning the adaption network and (ii) learning the adaption network.
An aspect of the present invention relates to a method for identifying data, comprising the steps of: acquiring original data; and, when synthesized data generated by synthesizing mark data with the original data is input to a learning model, generating, as identified data, synthesized data for which a result is output to be identical or similar to a result that is output as the original data is input to the learning model, wherein the mark data includes data for allowing the synthesized data and the original data to be differently recognized by a person.
METHOD FOR TRAINING AND TESTING DATA EMBEDDING NETWORK TO GENERATE MARKED DATA BY INTEGRATING ORIGINAL DATA WITH MARK DATA, AND TRAINING DEVICE AND TESTING DEVICE USING THE SAME
A method for learning a data embedding network is provided. The method includes steps of: a learning device acquiring and inputting original training data and mark training data into the data embedding network which integrates them and generates marked training data; inputting the marked training data into a learning network which applies a network operation to them and generates 1-st characteristic information, and inputting the original training data into the learning network which applies a network operation to them and generates 2-nd characteristic information; learning the data embedding network such that a data error is minimized, by referring to part of errors referring to the 1-st and the 2-nd characteristic information and errors referring to task specific outputs and their ground truths, and a marked data score is maximized, and learning a discriminator such that a original data score is maximized and the marked data score is minimized.
Method for training and testing data embedding network to generate marked data by integrating original data with mark data, and training device and testing device using the same
A method for learning a data embedding network is provided. The method includes steps of: a learning device acquiring and inputting original training data and mark training data into the data embedding network which integrates them and generates marked training data; inputting the marked training data into a learning network which applies a network operation to them and generates 1-st characteristic information, and inputting the original training data into the learning network which applies a network operation to them and generates 2-nd characteristic information; learning the data embedding network such that a data error is minimized, by referring to part of errors referring to the 1-st and the 2-nd characteristic information and errors referring to task specific outputs and their ground truths, and a marked data score is maximized, and learning a discriminator such that a original data score is maximized and the marked data score is minimized.
A method for concealing original data to protect personal information is provided. The method includes steps of: a data obfuscation device (a) if the original data is acquired, inputting the original data or its modified data into a learning network, and allowing the learning network to (i) apply a network operation to the original data or the modified data using learned parameters of the learning network and thus to (ii) output characteristic information on the original data or the modified data; and (b) updating the original data or the modified data via backpropagation using part of (i) 1-st losses calculated by referring to the characteristic information and its corresponding 1-st ground truth, and (ii) 2-nd losses calculated by referring to (ii-1) a task specific output generated by using the characteristic information (ii-2) a 2-nd ground truth corresponding to the task specific output, to thereby generate obfuscated data.
According to one aspect of the present invention, provided is a method for anonymizing data, the method comprising: a step for acquiring original data; and a step for generating, as anonymized data, obfuscated data obfuscated from the original data, wherein the result that is output when the obfuscated data is input to a learning model is identical or similar to the result that is output when the original data is input to the learning model.
Method for training and testing obfuscation network capable of processing data to be concealed for privacy, and training device and testing device using the same
A method for learning an obfuscation network used for concealing original data is provided. The method includes steps of: a learning device instructing the obfuscation network to obfuscate inputted training data, inputting the obfuscated training data into a learning network, and allowing the learning network to apply a network operation to the obfuscated training data and thus to generate 1-st characteristic information, and allowing the learning network to apply a network operation to the inputted training data and thus to generate 2-nd characteristic information, and learning the obfuscation network such that an error is minimized, calculated by referring to part of an error acquired by referring to the 1-st and the 2-nd characteristic information, and an error acquired by referring to a task specific output and its corresponding ground truth, and such that an error is maximized, calculated by referring to the training data and the obfuscated training data.
A method for concealing original data to protect personal information is provided. The method includes steps of: a data obfuscation device (a) if the original data is acquired, inputting the original data or its modified data into a learning network, and allowing the learning network to (i) apply a network operation to the original data or the modified data using learned parameters of the learning network and thus to (ii) output characteristic information on the original data or the modified data; and (b) updating the original data or the modified data via backpropagation using part of (i) 1-st losses calculated by referring to the characteristic information and its corresponding 1-st ground truth, and (ii) 2-nd losses calculated by referring to (ii-1) a task specific output generated by using the characteristic information and (ii-2) a 2-nd ground truth corresponding to the task specific output, to thereby generate obfuscated data.
METHOD FOR TRAINING AND TESTING OBFUSCATION NETWORK CAPABLE OF PROCESSING DATA TO BE CONCEALED FOR PRIVACY, AND TRAINING DEVICE AND TESTING DEVICE USING THE SAME
A method for learning an obfuscation network used for concealing original data is provided. The method includes steps of: a learning device instructing the obfuscation network to obfuscate inputted training data, inputting the obfuscated training data into a learning network, and allowing the learning network to apply a network operation to the obfuscated training data and thus to generate 1-st characteristic information, and allowing the learning network to apply a network operation to the inputted training data and thus to generate 2-nd characteristic information, and learning the obfuscation network such that an error is minimized, calculated by referring to part of an error acquired by referring to the 1-st and the 2-nd characteristic information, and an error acquired by referring to a task specific output and its corresponding ground truth, and such that an error is maximized, calculated by referring to the training data and the obfuscated training data.
09 - Scientific and electric apparatus and instruments
42 - Scientific, technological and industrial services, research and design
Goods & Services
Data transmission devices; computer software for data
processing; computer software to enable searching of data;
computer software for database management; computer software
for encryption; computer databases; computer software;
computer application software; computer software platforms;
data conversion apparatus; apparatus for processing,
transmitting and storing database information; data
processing apparatus; encryption apparatus; encoding and
decoding apparatus and instruments; encoding and decoding
apparatus; recorded data files; downloadable digital video
recordings; downloadable image files; recorded electronic
documents; downloadable electronic documents. Data warehousing; development of systems for the processing
of data; development of programmes for data processing;
database design and development; reconstitution of
databases; data security services; decryption of data; data
encryption services; engineering services relating to data
processing technology; design services for data processing
systems; technical advisory services relating to data
processing; development of computer software for data
processing; development of data processing apparatus; design
of data processing apparatus; design and development of
computer databases; software design and development
services; computer system design; development of computer
hardware; computer hardware and software design; design
services relating to the development of computerised
information processing systems.
09 - Scientific and electric apparatus and instruments
42 - Scientific, technological and industrial services, research and design
Goods & Services
Data transmission devices for voice, data or image transmission; recorded computer software for data processing; downloadable computer software for data processing; recorded computer software to enable searching of data; downloadable computer software to enable searching of data; recorded computer software for database management; downloadable computer software for database management; recorded computer software for encryption; downloadable computer software for encryption; computer databases, namely, recorded computer software for application and database integration; computer databases, namely, downloadable computer software for application and database integration; recorded computer software for use in database management; downloadable computer software for use in database management; recorded computer application software for mobile phones, namely, software for data processing; downloadable computer application software for mobile phones, namely, software for data processing; recorded computer software platforms for data anonymization; downloadable computer software platforms for data anonymization; data conversion apparatus, namely, data processors; apparatus, namely, electronic data processing apparatus for processing, transmitting and storing database information; data processing apparatus; encryption apparatus, namely, electronic encryption units; encoding and decoding apparatus and instruments; encoding and decoding apparatus; portable and handheld digital electronic devices for recording, organizing, transmitting, manipulating, and reviewing text, data, image, and audio files; downloadable digital video recording software for use in the safeguarding of digital files, including audio, video, text, binary, still images, graphics and multimedia files; downloadable image files containing anonymized video regarding encryption; recorded electronic documents, namely, recorded computer programmes for data anonymization; downloadable electronic documents in the field of information technology Data warehousing; development of systems for the processing of data; development of programmes for data processing; database design and development; reconstitution of databases systems for others; data security consultancy services; decryption of data services; data encryption services; engineering services relating to data processing technology; design services for data processing systems; technical advisory services relating to data processing; development of computer software for data processing; development of data processing apparatus; design of data processing apparatus; design and development of computer databases; software design and development services; computer system design; development of computer hardware; computer hardware and software design; design services relating to the development of computerized information processing systems
