Targeted Adversarial Attacks on Deep Reinforcement Learning Policies via Model Checking

Dennis Gross, Thiago Simão, Nils Jansen, Guillermo Pérez

2023

Abstract

Deep Reinforcement Learning (DRL) agents are susceptible to adversarial noise in their observations that can mislead their policies and decrease their performance. However, an adversary may be interested not only in decreasing the reward, but also in modifying specific temporal logic properties of the policy. This paper presents a metric that measures the exact impact of adversarial attacks against such properties. We use this metric to craft optimal adversarial attacks. Furthermore, we introduce a model checking method that allows us to verify the robustness of RL policies against adversarial attacks. Our empirical analysis confirms (1) the quality of our metric to craft adversarial attacks against temporal logic properties, and (2) that we are able to concisely assess a system’s robustness against attacks.

Paper Citation

in Harvard Style

Gross D., Simão T., Jansen N. and Pérez G. (2023). Targeted Adversarial Attacks on Deep Reinforcement Learning Policies via Model Checking. In Proceedings of the 15th International Conference on Agents and Artificial Intelligence - Volume 3: ICAART, ISBN 978-989-758-623-1, pages 501-508. DOI: 10.5220/0011693200003393

in Bibtex Style

@conference{icaart23,
author={Dennis Gross and Thiago Simão and Nils Jansen and Guillermo Pérez},
title={Targeted Adversarial Attacks on Deep Reinforcement Learning Policies via Model Checking},
booktitle={Proceedings of the 15th International Conference on Agents and Artificial Intelligence - Volume 3: ICAART,},
year={2023},
pages={501-508},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0011693200003393},
isbn={978-989-758-623-1},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 15th International Conference on Agents and Artificial Intelligence - Volume 3: ICAART,
TI - Targeted Adversarial Attacks on Deep Reinforcement Learning Policies via Model Checking
SN - 978-989-758-623-1
AU - Gross D.
AU - Simão T.
AU - Jansen N.
AU - Pérez G.
PY - 2023
SP - 501
EP - 508
DO - 10.5220/0011693200003393