arXiv cs.AI· CheolWon Na, Hao Ni, Lukasz Szpruch, Zhangyang Wang, Dhagash Mehta, Saurabh Nagrecha, Alejandro Lopez-Lira, Chanyeol Choi, Yongjae Lee, Jee-Hyong Lee·· 14 小时前AI 评分42
多智能体交易系统中的对抗漏洞：角色与架构维度的投毒攻击研究
Poisoning Agentic Alpha: Adversarial Vulnerabilities Across Roles and Architectures in Multi-Agent Trading Systems
AI 导读
研究首次系统实证了对抗信号如何进入基于 LLM 的多智能体交易系统并影响最终交易决策，覆盖 Analyst、Researcher、Trader、Risk Manager 四种角色与四种通信拓扑。实验基于 post-cutoff 数据、五种资产和两个目标方向，发现没有架构天然鲁棒：多数投票的保护效果取决于良性智能体的一致性，而攻陷终端决策节点可绕过上游防护。
正文 · 原文
Abstract:LLM-based multi-agent trading systems are moving from research prototypes to live deployments that control real assets. They ingest news and social media from the open web and pass it between agents, so a single corrupted signal can reach the final decision and cause financial loss. We study two adversaries that can introduce such signals without access to model internals: a low-barrier data adversary that plants manipulated content in web sources, and a compromised-agent adversary that tampers with an agent's prompt. To our knowledge, this is the first systematic empirical study in finance of how an adversarial signal enters a multi-agent trading system and whether it survives to alter the final trading decision. Along the role axis, we pair each of four roles---Analyst, Researcher, Trader, and Risk Manager---with an attack matched to its interface. Along the structural axis, we compare four communication topologies, interpreted with a simple parameter-free heuristic, the Adversarial Signal Preservation Score. Experiments on post-cutoff data span five assets and two target directions. We find that no architecture is inherently robust: majority voting offers conditional protection depending on benign-agent agreement, while compromising a terminal decision node can bypass upstream safeguards. These findings provide empirical insights for developing more effective defense strategies for multi-agent systems.
| Comments: | Added a Statistical Analysis section (Figure 9) |
| Subjects: | Artificial Intelligence (cs.AI); Computational Engineering, Finance, and Science (cs.CE); Cryptography and Security (cs.CR); Multiagent Systems (cs.MA) |
| Cite as: | arXiv:2608.24069 [cs.AI] |
| (or arXiv:2608.24069v2 [cs.AI] for this version) | |
| https://doi.org/10.48550/arXiv.2608.24069 arXiv-issued DOI via DataCite |
Submission history
From: CheolWon Na [view email]
[v1]
Tue, 25 Aug 2026 05:07:37 UTC (3,587 KB)
[v2]
Thu, 29 Oct 2026 07:28:19 UTC (3,422 KB)
来源：arXiv cs.AI · arxiv.org