LesenForschungRadarAnlageframework
Anmelden / Registrieren
← Zurück zur Lektüre
NewsThema · 虚假新闻攻击智能体Wesentlich1 Min. LesezeitDisconfirmAI Redaktion

Preprint: Fabricated News Achieves 62% Attack Success Rate Against AI Trading Agents, Far Exceeding Prompt Injection's 14%

New research indicates that for LLM trading agents, fake news poses a greater threat than traditional prompt injection, with surface-level credibility cues being key attack vectors.

2026-10-20 12:00 GMT+8

Researchers Mengxiao Wang and Nitesh Saxena published a preprint on arXiv on October 19, 2026, titled "Fake News, Real Crashes," introducing a systematic benchmark for "information injection" attacks against Large Language Model (LLM) financial trading agents. Unlike prompt injection, which aims to manipulate the model's instructions, information injection directly targets the external evidence, such as news feeds, that the agent trusts.

The study evaluated approximately 10,000 decisions across 15 U.S. stocks. Results showed that while traditional prompt injection achieved a 14% Attack Success Rate (ASR), fabricated news reached 62%. More surprisingly, two simple 30-word templates achieved a 100% success rate across all tested stocks.

The authors found that for fact-poisoning templates, surface form matters more than content: removing credibility cues like "BREAKING" tags or named sources dropped the ASR from 100% to 0%, even though the false claim itself remained unchanged. Additionally, attack effectiveness depended on the agent's state; for instance, a fake indicator panel scored 91% against an agent about to hold but only 12% against one about to buy.

Quellen

  • arxiv.org↗
Anmelden / Registrieren
LesenForschungRadarAnlageframework
Thema

虚假新闻攻击智能体

德州农工大学研究人员在预印本论文《Fake News, Real Crashes》中指出,针对大型语言模型(LLM)金融交易代理的“信息注入”攻击比传统的“提示注入”更具威胁性。研究发现,虚假新闻对LLM交易代理的攻击成功率高达62%,而提…

2 Schritte1 BeiträgeAktualisiert 2026-10-21 05:53

Wie es dazu kam

  1. 2026-10-19Mengxiao Wang和Nitesh Saxena提交预印本论文《Fake News, Real Crashes: Information Injection Attacks on LLM Financial Trading Agents》,系统评估了针对LLM交易代理的信息注入攻击。arxiv.org ↗
  2. 2026-10-20媒体发布报道,指出研究显示虚假新闻对AI交易代理的攻击成功率达62%,远超提示注入的14%,且表面可信度线索是关键因素。arxiv.org ↗

Was noch ungeklärt ist

  • 金融机构和交易平台将如何调整其AI代理的安全协议以应对高成功率的虚假新闻攻击?
  • 美国证券交易委员会(SEC)是否会出台具体法规来规范使用LLM进行自主交易的第三方代理?
  • 除了层级聚合外,是否有更有效的技术手段能在不牺牲交易效率的前提下识别并过滤带有虚假可信度线索的新闻?
Vollständiges Thema lesen →
Recherche fortsetzen →