arXiv Machine Learning
Constrained Black-Box Attacks Against Cooperative Multi-Agent Reinforcement Learning
Read the original on arXiv Machine Learning →The Flow has not summarised this story yet — read it at arXiv Machine Learning.
Related stories
arXiv AI
Oct 27
Vulnerability Analysis for Safe Multi-Agent Reinforcement Learning
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 AI
Oct 21
Vulnerability Analysis for Safe Multi-Agent Reinforcement
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 AI
Sep 1
SUB-PLAY: Adversarial Policies against Partially Observed Multi-Agent Reinforcement Learning Systems
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,...
arXiv AI
Oct 23
Black-Box Red-Teaming of Multi-Agent Systems via Reinforcement Learning
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 Machine Learning
Oct 5
Demonstration-Guided Observation Attacks on Black-Box Safe Reinforcement Learning Controllers for Robotic Systems
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...
arXiv Machine Learning
Oct 9
When to Intervene? State-Aware Sparse Manipulation in Federated Reinforcement Learning
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.