arXiv:2508.09275v3 Announce Type: replace Abstract: Collaborative multi-agent reinforcement learning (MARL) is increasingly deployed in critical domains, yet its vulnerability to adversarial perturba...
arXiv:2510.01264v2 Announce Type: replace Abstract: Progress in adversarial multi-agent reinforcement learning (MARL) for robotics has been hampered by a lack of shared, extensible infrastructure tha...
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...
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 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:2606. 16605v1 Announce Type: new Abstract: World models are widely used in robotic and agentic engineering control systems due to their ability to learn latent dynamics for planning and decision-making.
arXiv:2608. 04317v1 Announce Type: cross Abstract: Autonomous cyber defense systems based on Deep Reinforcement Learning (DRL) have attracted significant research attention, yet remain evaluated almost exclusively against static, heuristic red agents, leaving their robustness against adaptive threats critically understudied.
arXiv:2606. 13621v1 Announce Type: new Abstract: Shielded reinforcement learning is typically presented as a runtime safety mechanism that compiles temporal-logic specifications into automata restricting an agent's actions.
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:2510. 09041v3 Announce Type: replace-cross Abstract: Deep reinforcement learning (DRL) has demonstrated remarkable success in developing autonomous driving policies.
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.
Autonomous cyber defense systems based on Deep Reinforcement Learning (DRL) have attracted significant research attention, yet remain evaluated almost exclusively against static, heuristic red agents, leaving their robustness against adaptive threats critically understudied. Meanwhile, recent advances in Reinforcement Learning with Verifiable Rewards (RLVR) have improved LLM reasoning, but their integration into cybersecurity remains elusive due to the absence of suitable benchmark environments and interaction datasets.