Detection of Man-in-the-Middle Attacks in Model-Free Reinforcement Learning
This paper proposes a Bellman Deviation algorithm for the detection of man-in-the-middle (MITM) attacks occurring when an agent controls a Markov Decision Process (MDP) system using model-free reinforcement learning. We show an intuitive necessary and sufficient ``informational advantage" condition for the proposed algorithm to guarantee the detection of attacks with high probability, while also avoiding false alarms.
Email Address of Submitting Authorsairishi10@gmail.com
Submitting Author's InstitutionUniversity of California, San Diego
Submitting Author's Country
- United States of America