arXiv AI July 9, 2026 By Haowen Xu, Xue Tan, Lei Ma, Zhihao Zhang, Chao Wang, Qingze Wang, Ping Chen, Jun Dai, Xiaoyan Sun

When Agents Go Rogue: Activation-Based Detection of Malicious Behaviors in Multi-Agent Systems

Read the original on arXiv AI →

arXiv:2607. 06807v1 Announce Type: cross Abstract: While enabling effective collaboration on complex tasks, LLM-based Multi-Agent Systems (MAS) face critical security challenges due to vulnerabilities at the agent and interaction levels.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv AI.

arXiv Machine Learning

Aug 11

Benchmarking the Robustness of Agentic Systems to Adversarially-Induced Harms

arXiv:2508. 16481v3 Announce Type: replace Abstract: Ensuring the safe use of agentic systems requires a thorough understanding of the range of malicious behaviors these systems may exhibit.

By Jonathan N\"other, Adish Singla, Goran Radanovic

llms agents benchmarks safety

arXiv AI

Sep 2

SoK: When Safe Agents Fail Together: The Security of Multi Agent LLM Systems

arXiv:2609.00595v1 Announce Type: cross Abstract: Safe agents can fail together. Multi-agent LLM systems (MAS) move information, state, decisions, and authority across principal boundaries, creating...

By Rui Yang, Junjie Xu, Zhengyu Liu, Neil Fendley, Yang Hong, Ziyang Li, Yinzhi Cao

llms agents benchmarks

arXiv AI

Jun 30

MESA: Prioritizing Vulnerable Communication Channels for Securing Multi-Agent Systems

arXiv:2606. 30602v1 Announce Type: cross Abstract: Multi-agent systems (MAS) are increasingly used to automate complex, distributed workflows.

By Kunyang Li, Kyle Domico, Jonathan Gregory, Patrick McDaniel

llms agents benchmarks

arXiv AI

Jul 21

STAC: When Innocent Tools Form Dangerous Chains for LLM Agents

arXiv:2509. 25624v3 Announce Type: replace-cross Abstract: As LLMs advance into autonomous agents with tool-use capabilities, they introduce security challenges that extend beyond traditional content-based LLM safety concerns.

By Jing-Jing Li, Jianfeng He, Chao Shang, Devang Kulshreshtha, Xun Xian, Yi Zhang, Hang Su, Sandesh Swamy, Yanjun Qi

llms agents multimodal benchmarks safety

arXiv Machine Learning

4d ago

MCPTox: A Benchmark for Tool Poisoning Attack on Real-World MCP Servers

arXiv:2508.14925v2 Announce Type: replace-cross Abstract: By providing a standardized interface for LLM agents to interact with external tools, the Model Context Protocol (MCP) is quickly becoming a...

By Zhiqiang Wang, Yichao Gao, Yanting Wang, Suyuan Liu, Haifeng Sun, Haoran Cheng, Guanquan Shi, Haohua Du, Xiangyang Li

llms agents benchmarks safety

arXiv AI

Jun 16

A Survey on Agentic Security: Applications, Threats and Defenses

arXiv:2510. 06445v3 Announce Type: replace-cross Abstract: LLM-based agents are now used throughout cybersecurity.

By Asif Shahriar, Md Nafiu Rahman, Sadif Ahmed, Farig Sadeque, Md Rizwan Parvez

llms agents safety

One email a morning, machine-written

Related stories

Benchmarking the Robustness of Agentic Systems to Adversarially-Induced Harms

SoK: When Safe Agents Fail Together: The Security of Multi Agent LLM Systems

MESA: Prioritizing Vulnerable Communication Channels for Securing Multi-Agent Systems

STAC: When Innocent Tools Form Dangerous Chains for LLM Agents

MCPTox: A Benchmark for Tool Poisoning Attack on Real-World MCP Servers

A Survey on Agentic Security: Applications, Threats and Defenses