SafeFlow: Semantic Information-Flow Control for Blocking Malicious Propagation in Multi-Agent Systems

作者：Haowen Dai, Zonghao Ying, Wenfeng Li, XiangFan Wu, Yisong Xiao, Tianyuan Zhang, Jiaye Lin, Lei Wei, Guangyuan Dong, Xitong Ling, Xixun Lin, Quanchen Zou, Xiangzheng Zhang · 发表于：arXiv (Cornell University) · 年份：2026 · 研究领域：Security and Verification in Computing、Access Control and Trust、Multi-Agent Systems and Negotiation

Multi-agent systems improve capability through task decomposition and role specialization, but these same mechanisms introduce an important safety blind spot: a harmful objective can be fragmented into locally plausible subtasks, allowing malicious intent to evade detection by any single agent. This is a growing social-impact challenge: systems handling sensitive information or consequential tools can turn routine delegation into unauthorized disclosure or unsafe action. We argue that this failure mode is better understood as a semantic information-flow problem than as a single-turn prompt classification task. To address this, we propose SafeFlow, a defense framework for multi-agent systems that formalizes malicious cross-agent propagation as a semantic information-flow problem. SafeFlow attaches structured semantic taints to root requests, propagates them through a dynamic collaboration graph, and performs workflow-level validation to reconstruct the global risk context before irreversible actions are committed. Evaluated on four benchmarks spanning prompt injection, jailbreak-based unsafe tool use, risky code execution, and harmful web-agent behavior, SafeFlow reduces attack success rates compared to undefended baselines and external defenses while retaining high benign task completion and a high paired safe--harm success rate. Our findings show that multi-agent systems still lack mechanisms for preserving risk semantics across delegation boundaries. This gap can turn routi...