Lab member paper accepted at AAAI 2022

• Post by: Bahareh Arghavani
• February 17, 2023
• Comments off

Congratulations on the acceptance of your paper titled “Mitigation of Adversarial Policy Imitation via Constrained Randomization of Policy (CRoP)” This is a significant achievement that reflects your hard work, dedication, and expertise in the field of machine learning and artificial intelligence.

The paper is available on AAAI .

Your research has great potential to make a real impact on the development of more robust and reliable AI systems, which is an essential task in today’s rapidly evolving technological landscape. Your approach to using the Theory of Mind framework to mitigate adversarial communication at test time is innovative and promising, and we look forward to seeing the results of further research and development in this area.

Abstract :

Deep reinforcement learning (DRL) policies are vulnerable to unauthorized replication attacks, where an adversary exploits imitation learning to reproduce target policies from observed behavior. In this paper, we propose Constrained Randomization of Policy (CRoP) as a mitigation technique against such attacks. CRoP induces the execution of sub-optimal actions at random under performance loss constraints. We present a parametric analysis of CRoP, address the optimality of CRoP, and establish theoretical bounds on the adversarial budget and the expectation of loss. Furthermore, we report the experimental evaluation of CRoP in Atari environments under adversarial imitation, which demonstrate the efficacy and feasibility of our proposed method against policy replication attacks.

Author(s):

Nancirose Piazza and Vahid Behzadan