loading
Papers Papers/2022 Papers Papers/2022

Research.Publish.Connect.

Paper

Authors: Myria Bouhaddi and Kamel Adi

Affiliation: Computer Security Research Laboratory, University of Quebec in Outaouais, Gatineau, Quebec, Canada

Keyword(s): Deep Reinforcement Learning, Adversarial Attacks, Reward Poisoning Attacks, Optimal Defense Policy, Multi-Environment Training.

Abstract: Our research tackles the critical challenge of defending against poisoning attacks in deep reinforcement learning, which have significant cybersecurity implications. These attacks involve subtle manipulation of rewards, leading the attacker’s policy to appear optimal under the poisoned rewards, thus compromising the integrity and reliability of such systems. Our goal is to develop robust agents resistant to manipulations. We propose an optimization framework with a multi-environment setting, which enhances resilience and generalization. By exposing agents to diverse environments, we mitigate the impact of poisoning attacks. Additionally, we employ a variance-based method to detect reward manipulation effectively. Leveraging this information, our optimization framework derives a defense policy that fortifies agents against attacks, bolstering their resistance to reward manipulation.

CC BY-NC-ND 4.0

Sign In Guest: Register as new SciTePress user now for free.

Sign In SciTePress user: please login.

PDF ImageMy Papers

You are not signed in, therefore limits apply to your IP address 18.222.163.231

In the current month:
Recent papers: 100 available of 100 total
2+ years older papers: 200 available of 200 total

Paper citation in several formats:
Bouhaddi, M. and Adi, K. (2023). Multi-Environment Training Against Reward Poisoning Attacks on Deep Reinforcement Learning. In Proceedings of the 20th International Conference on Security and Cryptography - SECRYPT; ISBN 978-989-758-666-8; ISSN 2184-7711, SciTePress, pages 870-875. DOI: 10.5220/0012139900003555

@conference{secrypt23,
author={Myria Bouhaddi. and Kamel Adi.},
title={Multi-Environment Training Against Reward Poisoning Attacks on Deep Reinforcement Learning},
booktitle={Proceedings of the 20th International Conference on Security and Cryptography - SECRYPT},
year={2023},
pages={870-875},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0012139900003555},
isbn={978-989-758-666-8},
issn={2184-7711},
}

TY - CONF

JO - Proceedings of the 20th International Conference on Security and Cryptography - SECRYPT
TI - Multi-Environment Training Against Reward Poisoning Attacks on Deep Reinforcement Learning
SN - 978-989-758-666-8
IS - 2184-7711
AU - Bouhaddi, M.
AU - Adi, K.
PY - 2023
SP - 870
EP - 875
DO - 10.5220/0012139900003555
PB - SciTePress