公开(公告)号：EP4365787A1

公开(公告)日：2024-05-08

申请号：EP23206524.3

申请日：2023-10-27

申请人： Deutsche Telekom AG

发明人： ELOVICI, Yuval ,  BRODT, Oleg ,  SHABTAI, Asaf ,  GROLMAN, Edita ,  MIMRAN, David ,  KHAVKIN, Michael

IPC分类号： G06N20/20 ,  G06F21/57

CPC分类号： G06F21/577 ,  G06N20/20

摘要： A system for performing an assessment of the robustness and resilience of an examined original ML model against model extraction attacks, comprising a computerized device having at least one processor, which is adapted to train multiple candidate models MC with the external dataset D for each of the specified candidate learning algorithms α in Alg, where each candidate substitute model is trained on a subset of D corresponding to the evaluated ith query limit of the query budget constraint Q; evaluate the performance of each substitute model MC according to different evaluation methods ∈ Evaluation; calculate the robustness of each substitute model, where smaller difference or high agreement/similarity rate between the performance of the original model and the substitute model indicates that the original and substitute models are similar to each other, and that the substitute model having the highest performance can mimic the behavior of the original model and can be used as a replica of the original model.

公开(公告)号：EP3910479A1

公开(公告)日：2021-11-17

申请号：EP21173831.5

申请日：2021-05-14

申请人： Deutsche Telekom AG

发明人： ELOVICI, Yuval ,  SHABTAI, Asaf ,  BRODT, Oleg ,  MIMRAN, David ,  KHAVKIN, Michael ,  GROLMAN, Edita

IPC分类号： G06F11/36 ,  G06F21/57 ,  G06F21/62 ,  G06N20/00 ,  G06N5/02

摘要： A system for testing Machine Learning (ML) and deep learning models for robustness, and durability against adversarial bias and privacy attacks, comprising a Project Repository for storing metadata of ongoing projects each of which having a defined project policy, and created ML models and data sources being associated with the ongoing projects; a Secure Data Repository, for storing training and testing datasets and models used in each project for evaluating the robustness of the each project; a Data/Model Profiler for creating a profile, based on the settings and configurations of the datasets and the models; a Test Recommendation Engine for recommending the relevant and most indicative attacks/tests for each examined model and for creating indicative and effective test suites; a Test/Attack Ontology module for storing all attacks/tests with their metadata and mapping the attacks/tests to their corresponding settings and configurations; an Attack Repository for storing the implemented tests/attacks. An ML model is tested against each one of the robustness categories (privacy, bias and adversarial learning); a Test Execution Environment for Initializing a test suite, running multiple tests and prioritizing tests in the test suite; a Project/Test Analytics module for analyzing the test suite results and monitoring changes in performance over time; a Defenses Repository for storing implemented defense methods implemented for each robustness category.

公开(公告)号：EP4400973A1

公开(公告)日：2024-07-17

申请号：EP24151336.5

申请日：2024-01-11

申请人： Deutsche Telekom AG

发明人： MIMRAN, David ,  BRODT, Oleg ,  ELOVICI, Yuval ,  SHABTAI, Asaf ,  CHOI, Jinsung ,  LEHMANN, Heiko

IPC分类号： G06F11/30 ,  G06F11/34

CPC分类号： G06F11/3058 ,  G06F11/3062 ,  G06F11/302 ,  G06F2201/86520130101 ,  G06F11/3428

摘要： A system for computing an estimated energy consumption of a target program running on a specific computerized system, comprising a processor and associated memory, storing an application being run by the at least one processor, which are adapted to measure the energy consumption of every atomic action of the specific computerized system in different resolutions; create an energy cost for mapping between all atomic actions and their corresponding energy requirements for a specific computer system, on which the program will run; create a profile for the target program, in terms of which atomic actions of the specific computerized system are required for the execution of the target program on the specific computerized system; calculate the energy consumption of the target program, by calculating the amount of atomic actions related to the target program during its execution, multiplied by the energy consumption associated with every respective atomic action.

公开(公告)号：EP4020886A1

公开(公告)日：2022-06-29

申请号：EP21216471.9

申请日：2021-12-21

申请人： Deutsche Telekom AG

发明人： VAISMAN, Yizhak ,  COHEN, Dvir ,  ELOVICI, Yuval ,  SHABTAI, Asaf ,  BRODT, Oleg ,  MIMRAN, David

IPC分类号： H04L9/40

摘要： A system for detecting suspicious websites in proxy's data streams, comprising a data collection and pre-processing module for receiving data from proxy logs and transforming the data into temporal website sequences of length n, where each sequence is from a specific user and removing rare websites that appear only once; a training module being a neural network for receiving each the sequence and performing a training phase, during which each sequence corresponds to a user ID and generating a language model for predicting the next token (website) in each sequence; an anomaly detection module for receiving all the sequences and feeding the sequences into the trained model; providing by the model, for every sequence, a probability score representing how probable the sequence is; classifying the sequence as suspicious if the score is above a specific threshold t; an alerting module having an alert-logic for outputting alerts based on the number of suspicious websites of a user and the number of websites that were blocked by the proxy.

公开(公告)号：EP4009586A1

公开(公告)日：2022-06-08

申请号：EP21212905.0

申请日：2021-12-07

申请人： Deutsche Telekom AG

发明人： MIKITYUK, Alexandra ,  YIN, Ming ,  LAUFER, Viktoria Anna ,  AMIT, Guy ,  SHABTAI, Asaf ,  ELOVICI, Yuval ,  BRODT, Oleg ,  MIMRAN, David

IPC分类号： H04L9/40

摘要： A system for automated neutralization of fileless malware on connected IoT devices, each having a memory, for storing the device's operation software, a processor for sending commands to the device's components and a network card, for connects the device's processor to a data network. The system comprises a Feature Extractor module for receiving, collecting and analyzing data from the device's memory, the processor and the network card, and for recording measurements from the device and extracting the device's behavioral pattern; an Intrusion Detector, for examining the behavioral pattern received from the Feature Extractor and deciding whether there was a malware break/attack or there is a malfunction of the device itself; a Remediation Selector, that learns in real-time how different pre-defined actions affect the monitored devices for receiving from the Intrusion Detector decision if the is device under a malware attack and its kind, and sending remediation, repairing and neutralization commands to an LSTM Neural Network.

公开(公告)号：EP3971799A1

公开(公告)日：2022-03-23

申请号：EP21195587.7

申请日：2021-09-08

申请人： Deutsche Telekom AG

发明人： HACMON, Amit ,  ELOVICI, Yuval ,  SHABTAI, Asaf ,  GROLMAN, Edita ,  BRODT, Oleg ,  FISCHER, Sebastian ,  FROMM, Ronald

IPC分类号： G06N20/00 ,  G06F8/00 ,  G06F11/36

摘要： A system for the assessment of robustness and fairness of Al-based ML models, comprising a data/model profiler for creating an evaluation profile in the form of data and model profiles, based on the dataset and the properties of the ML model; a test recommendation engine that receives data and model profiles from the data/model profiler and recommends the relevant tests to be performed; a test repository that contains all the tests that can be examined; a test execution environment for gathering data related to all the tests that were recommended by the test recommendation engine; a final fairness score aggregation module for aggregating the executed tests results into a final fairness score of the examined model and dataset.

公开(公告)号：EP3968239A1

公开(公告)日：2022-03-16

申请号：EP21195248.6

申请日：2021-09-07

申请人： Deutsche Telekom AG

发明人： FISCHER, Sebastian ,  FROMM, Ronald ,  HACMON, Amit ,  ELOVICI, Yuval ,  GROLMAN, Edita ,  BRODT, Oleg ,  SHABTAI, Asaf

IPC分类号： G06N3/08 ,  G06N3/04 ,  G06N20/00

摘要： A system for bias estimation in Artificial Intelligence (Al) models using a pre-trained unsupervised deep neural network, comprising a bias vector generator implemented by at least one processor that executes an unsupervised DNN with a predetermined loss function. The bias vector generator is adapted to store a given ML model to be examined, with predetermined features; store a test-set of one or more test data samples being input data samples; receive a feature vector consisting of one or more input samples; output a bias vector indicating the degree of bias for each feature, according to said one or more input samples. The system also comprises a post-processor which is adapted to receive a set of bias vectors generated by said bias vector generator; process said bias vectors; calculate a bias estimation for every feature of said ML model, based on predictions of said ML model; provide a final bias estimation for each examined feature.

公开(公告)号：EP4362426A1

公开(公告)日：2024-05-01

申请号：EP23206527.6

申请日：2023-10-27

申请人： Deutsche Telekom AG

发明人： ELOVICI, Yuval ,  BRODT, Oleg ,  SHABTAI, Asaf ,  MIMRAN, David ,  PUZIS, Rami

IPC分类号： H04L67/104 ,  H04L67/1074 ,  H04L67/568 ,  H04L67/289

CPC分类号： H04L67/1085 ,  H04L67/1076 ,  H04L67/535 ,  H04L67/289 ,  H04L67/288 ,  H04L67/2885

摘要： A method for on demand matching between unused suppliers resources and consumers, comprising the steps of: implementing, on a computerized device (such as a server) with at least one processor, a resilient and trusted ad-hoc Peer-To-Peer (P2P) communication protocol across connected devices for sharing browsed content among an ad-hoc group of connected devices, using WiFi networking capabilities of the connected devices; optimizing, by the computerized device, internet consumption across browser based sessions, using standalone browsers, or browsers' modules utilized by native applications; replicating, by the computerized device, browser cache assets of participating devices, based on usage patterns and top internet destinations; refreshing, by the computerized device, shared cache assets in idle time for utilizing bandwidth across the ad hoc group; measuring, by the computerized device, internet experience optimization ratio over a predetermined period of time by monitoring the performance of devices participating in Home CDN vs. the devices that are not connected to a local network; measuring, by the computerized device, internet experience optimization ratio across multiple local networks setups.

公开(公告)号：EP3190769B1

公开(公告)日：2020-10-28

申请号：EP16206471.1

申请日：2016-12-22

申请人： Deutsche Telekom AG

发明人： SHABTAI, Asaf ,  PUZIS, Rami ,  SILBERSCHLAG, Shimon ,  ROSHANDEL, Mehran

IPC分类号： H04L29/06

公开(公告)号：EP3719685A1

公开(公告)日：2020-10-07

申请号：EP20167836.4

申请日：2020-04-02

申请人： Deutsche Telekom AG

发明人： COHEN, Dvir ,  SHABTAI, Asaf ,  ELOVICI, Yuval ,  MIRSKY, Yisroel Avraham ,  PUZIS, Rami ,  MARTIN, Tobias ,  KAMP, Manuel

IPC分类号： G06F21/57 ,  H04L29/06

摘要： A system for analyzing and clustering darknet traffic streams with word embeddings, comprising a data processing module which collects packets that are sent to non-existing IP addresses that belong to darknet's taps (blackholes) that are deployed over the internet; a port embedding module for performing port sequence embeddings by using a word embedding algorithm on the port sequences extracted from the data processing module while transforming the port sequences into a meaningful numerical feature vectors; a clustering module for performing temporal clustering of the feature vectors over time; and an alert logic and visualization module visualizes the data and provides alerts regarding a cluster that an analyst classified as malicious in the past.