Machine learning systems and methods for reducing the false positive malware detection rate
Номер патента: EP4139821A2
Опубликовано: 01-03-2023
Автор(ы): Andreea DINCU, Daniel DICHIU, Elena A. BOSINCEANU, Razvan PREJBEANU, Robert-mihail BOTARLEANU, Sorina N. ZAMFIR
Принадлежит: Bitdefender IPR Management Ltd
Опубликовано: 01-03-2023
Автор(ы): Andreea DINCU, Daniel DICHIU, Elena A. BOSINCEANU, Razvan PREJBEANU, Robert-mihail BOTARLEANU, Sorina N. ZAMFIR
Принадлежит: Bitdefender IPR Management Ltd
Реферат: In some embodiments, a behavior classifier comprises a set of neural networks trained to determine whether a monitored software entity is malicious according to a sequence of computing events caused by the execution of the respective entity. When the behavior classifier indicates that the entity is malicious, some embodiments execute a memory classifier comprising another set of neural networks trained to determine whether the monitored entity is malicious according to a memory snapshot of the monitored entity. Applying the classifiers in sequence may substantially reduce the false positive detection rate, while reducing computational costs.
Computer-based systems configured for utilization of a trained detection machine learning model for activity determination and methods of use thereof
Номер патента: US12105795B2. Автор: Joshua Edwards,Tyler Maiman,Asher SMITH-ROSE,Shabnam KOUSHA. Владелец: Capital One Services LLC. Дата публикации: 2024-10-01.