SAJA: A State-action Joint Attack Framework On Multi-agent Deep Reinforcement Learning
2025 · Weiqi Guo, Guanjun Liu, Ziyuan Zhou
Abstract
Multi-Agent Deep Reinforcement Learning (MADRL) has shown potential for cooperative and competitive tasks such as autonomous driving and strategic gaming. However, models trained by MADRL are vulnerable to adversarial perturbations on states and actions. Therefore, it is essential to investigate the robustness of MADRL models from an attack perspective. Existing studies focus on either state-only attacks or action-only attacks, but do not consider how to effectively joint them. Simply combining state and action perturbations such as randomly perturbing states and actions does not exploit their potential synergistic effects. In this paper, we propose the State-Action Joint Attack (SAJA) framework that has a good synergistic effects. SAJA consists of two important phases: (1) In the state attack phase, a multi-step gradient ascent method utilizes both the actor network and the critic network to compute an adversarial state, and (2) in the action attack phase, based on the perturbed state
Authors
(none)
Tags
Stats
Related papers
- Constrained Black-box Attacks Against Cooperative Multi-agent Reinforcement Learning (2025)0.00
- A Spatiotemporal Stealthy Backdoor Attack Against Cooperative Multi-agent Deep Reinforcement Learning (2024)0.00
- Joint Intrinsic Motivation For Coordinated Exploration In Multi-agent Deep Reinforcement Learning (2024)0.00
- What Is The Solution For State-adversarial Multi-agent Reinforcement Learning? (2022)0.00
- SUB-PLAY: Adversarial Policies Against Partially Observed Multi-agent Reinforcement Learning Systems (2024)0.00
- Sok: Adversarial Machine Learning Attacks And Defences In Multi-agent Reinforcement Learning (2023)10.74
- Camouflage Adversarial Attacks On Multiple Agent Systems (2024)0.00
- Neutral Agent-based Adversarial Policy Learning Against Deep Reinforcement Learning In Multi-party Open Systems (2025)0.00