Paul Montague

Feature-Space Bayesian Adversarial Learning Improved Malware Detector Robustness

2023 · Proceedings of the AAAI Conference on Artificial Intelligence

We present a new algorithm to train a robust malware detector. Malware is a prolific problem and malware detectors are a front-line defense. Modern detectors rely on machine learning algorithms. Now, the adversarial objective is …

Fox in the Henhouse: Supply-Chain Backdoor Attacks Against Reinforcement Learning

2025 · arXiv (Cornell University)

The current state-of-the-art backdoor attacks against Reinforcement Learning (RL) rely upon unrealistically permissive access models, that assume the attacker can read (or even write) the victim's policy parameters, observations, or rewards. In this work, we …