Patent · US Active

Adversarial resilient malware detector randomization method and devices

US11822651B2 · kind B2 · utility

1Cited by

1References

20Claims

0Family size

Assignee

The Regents of the University of California · US

Inventors

Houman Homayoun · Fairfax, US
Prasant Mohapatra · Davis, US
Han-Che Wang · Tangxia, CN
Setareh Rafatirad · San Jose, US

Key dates

Filing date	Sep 22, 2021
Grant date	Nov 21, 2023
Priority date	—
Expiry date	Jul 28, 2042

Classification

Technology area (CPC G)Physics
CPC primaryG06F2221/034
WIPO fieldComputer technology
WIPO sectorElectrical engineering

Abstract

The embodiments disclose a system and method including a random number generator coupled to the randomized machine learning-based malware detector configured for determining changes of settings and selections of parameters, candidate classifiers integrated with the randomized machine learning-based malware detector and configured to be initiated by a random number to avoid transferable learning, a set of feature combinations for random feature selection including monitoring granularity and detection prediction latency and a random number for identifying a set of feature combinations that minimize the overhead and maintain enough variance in data for baffling the malware adversarial attacks.

Source: USPTO / EPO open patent data. Objective bibliographic and citation counts.