AI Paper Atlas

Research map / Multi-agent systems and games / LLM agents

A2ASecBench: A Protocol-Aware Security Benchmark for Agent-to-Agent Multi-Agent Systems

Tianhao Li, Chuangxin Chu, Yujia Zheng, Bohan Zhang, Neil Zhenqiang Gong, Chaowei Xiao

ICLR 2026 · Multi-agent systems and games › LLM agents · approach: Agent safety and attack benchmarks

Read the paperCheck your idea against 137,217 papers

AI-extracted summary. Written by AI from the paper's full text. Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Presents A2ASecBench, a protocol-aware security benchmark and first comprehensive security evaluation of agent-to-agent (A2A) multi-agent systems built on LLMs.

Problem

Agent-to-agent protocols enable interoperability among LLM-based multi-agent systems but introduce new security vulnerabilities that are not systematically evaluated.

Approach

A taxonomy of A2A-specific threats paired with a benchmark that evaluates security of A2A-MAS in a protocol-aware way; the abstract is truncated so specifics beyond the taxonomy and benchmark are not stated.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
increase number of injected lookalike AgentCards from 3 to 7 (ablation)AgentCard Spoofing · A2A discoveryASR: 76% -> 87% -> 95%Improved
embed a cloaked agent in the multi-agent systemA2A-MAS benign tasks · Healthcare utilityutility score: 0.872 -> 0.595Hurt
embed a cloaked agent in the multi-agent systemA2A-MAS benign tasks · Travel utilityutility score: 0.853 -> 0.682Hurt
embed a cloaked agent in the multi-agent systemA2A-MAS benign tasks · Finance utilityutility score: 0.962 -> 0.749Hurt
add NeMo Guardrails as a security gatewayA2A-MAS · Agent-Side Request ForgeryASR: ASR 0.23-0.48 remainsImproved
add NeMo Guardrails as a security gatewayA2A-MAS · Half-Open Task Flooding and Artifact-Triggered Script InjectionASR: HOTF 0.85-0.91, ATSI 0.91-0.94No clear effect
add NeMo Guardrails as a security gatewayA2A-MAS · Cycle OverflowASR: 1.00 -> 0.66-0.73Mixed
transfer attack patterns to ANP protocolattack patterns · ANPASR: AS 0.98, others 1.00Hurt

Experimental setup

Benchmarks: A2ASecBench

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy