Methods and systems for fingerprinting malicious behavior
Номер патента: EP4449286A1
Опубликовано: 23-10-2024
Автор(ы): Sameer Shashikant Paranjape
Принадлежит: BlackBerry Ltd
Опубликовано: 23-10-2024
Автор(ы): Sameer Shashikant Paranjape
Принадлежит: BlackBerry Ltd
Реферат: Methods and systems for fingerprinting a malicious behavior. In a first stage of training, a coarse machine learning one-class classifier is trained to detect a first dataset of events, the first dataset of events including a dataset of events representing a malicious behavior and a dataset of events representing non-malicious behavior and a benign machine learning one-class classifier is trained to detect a second dataset of events, the second dataset of events excluding the dataset of events representing malicious activity. An ensemble of models including the benign and coarse machine learning one-class classifiers is applied to the first dataset of events to create a third training set representing the malicious behavior for a second stage of training. A final machine learning one-class classifier is trained in the second stage of training using the third training set. The final machine learning one-class classifier represents a fingerprint of the malicious behavior.
Method and data processing system for detecting a malicious component on an integrated circuit
Номер патента: US11914703B2. Автор: Ventzislav Nikov,Nikita Veshchikov. Владелец: NXP BV. Дата публикации: 2024-02-27.