FAME

Published:

FAME has been designed to evaluate ML-based malware classifiers against adversarial examples. It aims to provide understanding on how byte-level transformations can be injected into Windows Portable Executable (PE) files and compromise models. Moreover, it supports integrity verification to ensure that the adversarial examples remain valid after manipulation.

Download: pip install famework

Papers: ARMED, AIMED, GAME-UP
Source: GitHub and PyPI