{"ID":2835367,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2511.22924","arxiv_id":"2511.22924","title":"MAS-Shield: A Defense Framework for Secure and Efficient LLM MAS","abstract":"Large Language Model (LLM)-based Multi-Agent Systems (MAS) are susceptible to linguistic attacks that can trigger cascading failures across the network. Existing defenses face a fundamental dilemma: lightweight single-auditor methods are prone to single points of failure, while robust committee-based approaches incur prohibitive computational costs in multi-turn interactions. To address this challenge, we propose \\textbf{MAS-Shield}, a secure and efficient defense framework designed with a coarse-to-fine filtering pipeline. Rather than applying uniform scrutiny, MAS-Shield dynamically allocates defense resources through a three-stage protocol: (1) \\textbf{Critical Agent Selection } strategically targets high-influence nodes to narrow the defense surface; (2) \\textbf{Light Auditing} employs lightweight sentry models to rapidly filter the majority of benign cases; and (3) \\textbf{Global Consensus Auditing} escalates only suspicious or ambiguous signals to a heavyweight committee for definitive arbitration. This hierarchical design effectively optimizes the security-efficiency trade-off. Experiments demonstrate that MAS-Shield achieves a 92.5\\% recovery rate against diverse adversarial scenarios and reduces defense latency by over 70\\% compared to existing methods.","short_abstract":"Large Language Model (LLM)-based Multi-Agent Systems (MAS) are susceptible to linguistic attacks that can trigger cascading failures across the network. Existing defenses face a fundamental dilemma: lightweight single-auditor methods are prone to single points of failure, while robust committee-based approaches incur p...","url_abs":"https://arxiv.org/abs/2511.22924","url_pdf":"https://arxiv.org/pdf/2511.22924v2","authors":"[\"Kaixiang Wang\",\"Zhaojiacheng Zhou\",\"Bunyod Suvonov\",\"Jiong Lou\",\"Jie LI\"]","published":"2025-11-28T06:55:50Z","proceeding":"cs.MA","tasks":"[\"cs.MA\",\"cs.AI\",\"cs.CR\"]","methods":"[\"Large Language Model\",\"Language Model\"]","has_code":false}