L4DC_Correction.pdf (354.13 kB)

Detection of Man-in-the-Middle Attacks in Model-Free Reinforcement Learning

Download (354.13 kB)
posted on 2023-04-05, 20:16 authored by Rishi RaniRishi Rani

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 Author

Submitting Author's Institution

University of California, San Diego

Submitting Author's Country

  • United States of America