Distributed Detection of Adversarial Attacks in Multi-Agent Reinforcement Learning with Continuous Action Space
Fuente:
arXiv
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866911317685698560 |
|---|---|
| author | Kazari, Kiarash Shereen, Ezzeldin Dán, György |
| author_facet | Kazari, Kiarash Shereen, Ezzeldin Dán, György |
| contents | We address the problem of detecting adversarial attacks against cooperative multi-agent reinforcement learning with continuous action space. We propose a decentralized detector that relies solely on the local observations of the agents and makes use of a statistical characterization of the normal behavior of observable agents. The proposed detector utilizes deep neural networks to approximate the normal behavior of agents as parametric multivariate Gaussian distributions. Based on the predicted density functions, we define a normality score and provide a characterization of its mean and variance. This characterization allows us to employ a two-sided CUSUM procedure for detecting deviations of the normality score from its mean, serving as a detector of anomalous behavior in real-time. We evaluate our scheme on various multi-agent PettingZoo benchmarks against different state-of-the-art attack methods, and our results demonstrate the effectiveness of our method in detecting impactful adversarial attacks. Particularly, it outperforms the discrete counterpart by achieving AUC-ROC scores of over 0.95 against the most impactful attacks in all evaluated environments. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2508_15764 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Distributed Detection of Adversarial Attacks in Multi-Agent Reinforcement Learning with Continuous Action Space Kazari, Kiarash Shereen, Ezzeldin Dán, György Machine Learning Multiagent Systems We address the problem of detecting adversarial attacks against cooperative multi-agent reinforcement learning with continuous action space. We propose a decentralized detector that relies solely on the local observations of the agents and makes use of a statistical characterization of the normal behavior of observable agents. The proposed detector utilizes deep neural networks to approximate the normal behavior of agents as parametric multivariate Gaussian distributions. Based on the predicted density functions, we define a normality score and provide a characterization of its mean and variance. This characterization allows us to employ a two-sided CUSUM procedure for detecting deviations of the normality score from its mean, serving as a detector of anomalous behavior in real-time. We evaluate our scheme on various multi-agent PettingZoo benchmarks against different state-of-the-art attack methods, and our results demonstrate the effectiveness of our method in detecting impactful adversarial attacks. Particularly, it outperforms the discrete counterpart by achieving AUC-ROC scores of over 0.95 against the most impactful attacks in all evaluated environments. |
| title | Distributed Detection of Adversarial Attacks in Multi-Agent Reinforcement Learning with Continuous Action Space |
| topic | Machine Learning Multiagent Systems |
| url | https://arxiv.org/abs/2508.15764 |