#adversarial ml

2021-04-01

Malware bypass research using reinforcement learning.

2018-01-26 Hyrum S. Anderson, Anant Kharkar, Bobby Filar, David Evans, Phil Roth arXiv preprint

An RL agent that learns to make non-breaking modifications to malicious PE binaries to evade static ML-based malware classifiers.

2016-10-28 Hyrum S. Anderson, Jonathan Woodbridge, Bobby Filar 9th ACM Workshop on Artificial Intelligence and Security (AISec)

A GAN-style approach to generating adversarial domain names that evade DGA classifiers — and using the same setup to train a more robust detector.