paper-with-me

Papers

Interaction-Breaking Adversarial Learning Framework for Robust Multi-Agent Reinforcement Learning

2026-05-18 · Sunwoo Lee, Mingu Kang, Yonghyeon Jo, Seungyul Han arxiv

Cooperation is central to multi-agent reinforcement learning (MARL), yet learned coordination can be fragile when external perturbations disrupt inter-agent interactions. Prior robust MARL methods have primarily considered value-oriented attacks, leaving a gap in robustness when interaction structures themselves are corrupted. In this paper, we propose an interaction-breaking adversarial learning (IBAL) framework that takes an information-theoretic view to construct attacks that impede coordination by perturbing agents' observations and actions, and trains agents to perform reliably under such disruptions. Empirically, our approach improves robustness over existing robust MARL baselines across diverse attack settings and yields stronger performance even under agent-missing scenarios. Our code is available at https://sunwoolee0504.github.io/IBAL.

📄 PDF Abstract BibTeX arXiv:2605.18024

Code (0)

등록된 구현이 없습니다.

Tasks

Multi-agent Reinforcement Learning

Similar Papers 제목 키워드 기반

A Dynamic Stackelberg Game Framework for Agentic AI Defense Against LLM Jailbreaking

2025-07-10 · Zhengye Han, Quanyan Zhu

As large language models (LLMs) are increasingly deployed in critical applications, the challenge of jailbreaking, where adversaries manipulate the models to bypass safety mechanisms, has become a significant concern. Th…

AutoAdv: Automated Adversarial Prompting for Multi-Turn Jailbreaking of Large Language Models

2025-11-04 · Aashray Reddy, Andrew Zagula, Nicholas Saban arxiv

Large Language Models (LLMs) remain vulnerable to jailbreaking attacks where adversarial prompts elicit harmful outputs. Yet most evaluations focus on single-turn interactions while real-world attacks unfold through adap…

Agent Smith: A Single Image Can Jailbreak One Million Multimodal LLM Agents Exponentially Fast

2024-02-13 · Xiangming Gu, Xiaosen Zheng, Tianyu Pang, Chao Du 외

A multimodal large language model (MLLM) agent can receive instructions, capture images, retrieve histories from memory, and decide which tools to use. Nonetheless, red-teaming efforts have revealed that adversarial imag…

Language ModellingLarge Language ModelMultimodal Large Language ModelRed Teaming

Na'vi or Knave: Jailbreaking Language Models via Metaphorical Avatars

2024-12-10 · Yu Yan, Sheng Sun, Junqi Tong, Min Liu 외

Metaphor serves as an implicit approach to convey information, while enabling the generalized comprehension of complex subjects. However, metaphor can potentially be exploited to bypass the safety alignment mechanisms of…

Safety Alignment

Smarter Saboteurs, Better Fixers: Scaling & Security in Linear Multi-Agent Workflows

2026-06-10 · Timothy McAllister, Sina Abdidizaji, Ivan Garibay, Ozlem Ozmen Garibay arxiv

As LLM-based multi-agent systems (MAS) are deployed in the wild, the resilience of their collaboration structures against adversarial compromise becomes a critical safety concern. Attackers may leverage prompt-injection …