arXiv:2610.27293v2 Announce Type: replace Abstract: Safe Multi-Agent Reinforcement Learning (SMARL) aims to learn cooperative control policies under prescribed safety constraints. Al- though existing...
The paper examines inference‑time observation attacks on Safe Multi‑Agent Reinforcement Learning (SMARL), where an adversary perturbs observations of some agents to alter their actions. It introduces the MinMax Attack framework, which jointly selects adversarial target actions for compromised agents while considering the cooperative resistance of benign agents. The authors derive a bound on the induced safety cost and show through experiments that MinMax Attack causes higher safety costs than existing baselines while maintaining task reward, thus improving attack effectiveness and stealthiness.
arXiv:2402.03741v4 Announce Type: replace-cross Abstract: Recent advancements in multi-agent reinforcement learning (MARL) have opened up vast application prospects, such as swarm control of drones,...
The paper introduces ReMAS, a reinforcement learning-based framework for black-box red-teaming of multi-agent systems (MAS) that fine-tunes attacker LLMs to craft adversarial prompts. ReMAS operates in two stages: a rewrite stage that refines base attack prompts to boost extraction success, and a template generation stage that builds attack templates to better invoke specific sub-agents and expose their system prompts. Experiments demonstrate that ReMAS significantly outperforms existing black-box attacks, showing high success rates and transferability across different backend LLMs and MAS structures.
arXiv:2602.16543v2 Announce Type: replace Abstract: Safe reinforcement learning (Safe RL) learns robotic controllers that optimize task rewards under safety constraints, yet observation perturbations...
The paper introduces the Viability‑constrained Behavioral Steering Attack (V‑BSA), a new attack strategy for federated reinforcement learning that targets the timing of interventions rather than just the construction of malicious updates. By selecting sparse intervention states based on local policy uncertainty and applying envelope‑constrained steering, V‑BSA can significantly degrade performance on discrete‑action benchmarks while using far fewer interventions than traditional dense poisoning attacks. The study demonstrates that the specific states at which interventions occur constitute a distinct and critical dimension of robustness in sequential decision‑making settings.
arXiv:2403. 00420v3 Announce Type: replace-cross Abstract: Deep Reinforcement Learning (DRL) is a subfield of machine learning for training autonomous agents that take sequential actions across complex environments.
The paper introduces Adversarial Importance Sampling (Advis), a technique that leverages importance sampling over standard training trajectories to estimate and optimize worst‑case returns without extra environment interactions or auxiliary networks, thereby capturing long‑term robustness. It also presents advrl, a modular PyTorch library that consolidates existing robustness methods and adversarial attacks into single‑file implementations for easier prototyping and reproducible evaluation. Finally, the authors highlight that optimal adversarial hyperparameters do not transfer across agents, prompting evaluation against a broader set of attackers (6–14× more configurations) and demonstrate the effectiveness of their approach on continuous control tasks.
arXiv:2503. 01734v3 Announce Type: replace-cross Abstract: Attacks on machine learning models have been extensively studied through stateless optimization.
The paper surveys 86 recent studies on the security of reinforcement learning (RL) in autonomous driving. It systematically categorizes attacks and defenses by threat models and single- versus multi-agent settings, addressing gaps in previous surveys. The authors also evaluate how current attacks and defenses apply to autonomous driving, offering guidance for building robust RL systems.
arXiv:2606. 29867v1 Announce Type: cross Abstract: Deep Reinforcement Learning (DRL) has achieved significant success in robotics and autonomous systems, yet remains vulnerable to adversarial perturbations that can severely degrade performance.
arXiv:2610.06083v2 Announce Type: replace Abstract: Most adversarial attacks on deep reinforcement learning (DRL) assume white-box access to the victim policy, which rarely holds in practice. This pa...