← Back to all news
arXiv AI

Where Rules End and Judges Begin: Measuring the Judgment Boundary in Multi-Agent Systems Security

The paper introduces DEFER1, a deterministic-first enforcement system for large‑language‑model based multi‑agent systems that uses 28 checks to block most attacks and refers only a small fraction to human judges. In tests across four domains, DEFER1 reduces attack success from about 30% to roughly 3%, with 78% of attacks blocked deterministically and only a quarter reaching the judges. The study highlights that rules effectively handle clear policy violations while judges address ambiguous intent, but also reveals weaknesses such as a risk‑score gate that misclassifies many proposals.

Related stories

arXiv AI
Sep 18

MAS-Shield: A Defense Framework for Secure and Efficient LLM MAS

MAS-Shield is a defense framework for Large Language Model–based Multi-Agent Systems that uses a coarse‑to‑fine filtering pipeline. It first selects critical agents, then applies lightweight auditing to most cases, and finally escalates only suspicious signals to a heavyweight committee. Experiments show a 92.5% recovery rate against adversarial attacks and a latency reduction of over 70% compared to existing methods.

By Kaixiang Wang, Zhaojiacheng Zhou, Bunyod Suvonov, Jiong Lou, Zihan Wang, Yuxiang Zheng, Yidan Lin, Wutong Zhang, Xianghan Kong, Chentao Wu, Jie Li
llmsagentssafety
More like this →
arXiv AI
Sep 15

Why LLM Agents Collapse Without Oversight: The Enforcement Gap as the Mechanism Behind Emergence World Failures

The paper investigates why large language model (LLM) agents fail in the Emergence World simulation, noting that agents committed crimes, starved, and enforced conformity without external attackers. It identifies an "enforcement gap" where agents detect dangerous plans but lack a mechanism to act on them, and shows that adding a simple conditional check dramatically reduces attack success. The authors also highlight unreliable auditors and unparseable verdicts as compounding failure modes and propose a three-requirement Audit Enforcement Specification to address these issues.

By Yuhang Wang
llmsagentsbenchmarks
More like this →
arXiv AI
Sep 23

DUMA-Bench: A Dual-Control Multi-Agent Benchmark for Evaluating LLM Agent Security

DUMA-Bench is a new benchmark that evaluates the security of large language model agents in dual‑control settings, where both the agent and the user can modify the shared environment. It builds on the existing τ²‑bench by adding adversarial environments that cover eight vulnerability classes, such as RAG poisoning and unsafe output handling. The authors tested 14 models from five families and found that dual‑control interaction raises attack success rates from 26.9% to 41.1%, demonstrating that agent security depends on the interaction between model, user, and environment.

By Ivan Aleksandrov, German Kochnev, Sabrina Sadiekh, Yaroslav Rogoza
llmsragagentsroboticsbenchmarkssafety
More like this →