交易大厅上的传染：对抗性信号如何在多智能体交易系统中传播
Contagion on the Trading Floor: How Adversarial Signals Spread in Multi-Agent Trading Systems
浏览论文内容
中文总结 AI 辅助
本研究提出GMATS框架，揭示LLM多智能体交易系统对社交媒体注入的对抗性攻击的脆弱性，并证明通过优化拓扑和提示可提升鲁棒性。
中文摘要 AI 辅助
基于大型语言模型（LLM）的多智能体交易系统开始出现在量化金融领域，但其对对抗性输入的鲁棒性在很大程度上是未知的。我们研究了LLM交易栈在面对黑盒、仅输入攻击时的脆弱性，这些攻击仅通过允许的社交媒体信息流进入。我们引入了通用多智能体交易系统（GMATS），这是一个捕捉现代多智能体交易架构的框架，并实例化了一类黑盒投毒攻击者，这些攻击者将LLM视为帖子生成器，并将预算受限、看似良性的社交媒体内容注入分析师的信息流中。我们定义了传染指标，用于追踪对抗性内容如何在系统中传播，包括分析师和协调器层的信念转移分数，以及标准回测指标上的攻击清除增量。在包含历史市场和社会数据的安全离线基准上的实验表明，即使是简单的仅输入攻击者也能显著恶化风险收益特征，大幅降低夏普比率。同时，我们发现，适当设计的多智能体拓扑和协调器提示可以在相同的投毒预算下抑制对抗性冲击，并提高平均鲁棒性。
英文摘要
Multi-agent trading systems built on large language models (LLMs) are beginning to appear in quantitative finance, yet their robustness to adversarial inputs is largely unknown. We study the vulnerability of LLM trading stacks to black-box, input-only attacks that enter solely via admissible social-media feeds. We introduce the Generic Multi-Agent Trading System (GMATS), a framework that captures modern multiagent trading architectures and instantiate a class of black-box poisoning attackers that treat an LLM as a post generator and inject budget-constrained, plausibly benign social-media content into the analyst's evidence stream. We define contagion metrics that trace how adversarial content propagates through the stack, including belief-shift scores at analyst and coordinator layers and attack-clean deltas on standard backtest metrics. Experiments on a safe offline benchmark with historical market and social data show that even simple input-only attackers can materially degrade risk-return profiles, sharply reducing Sharpe ratios. At the same time, we find that suitably designed multi-agent topologies and coordinator prompts can dampen adversarial shocks and improve average robustness under identical poisoning budgets.
发表机构
- Nanyang Technological University（南洋理工大学）
- Centre for Frontier AI Research, IHPC, A*STAR（前沿人工智能研究中心，高性能计算研究所，新加坡科技研究局）
- National University of Singapore（新加坡国立大学）
机构由 AI 辅助整理，请以论文原文为准。
