发现信息
- 作者:Qiusi Zhan, Zhixiang Liang, Zifan Ying, Daniel D. Kang
- 年份:2024
- 发表源:Findings of the Association for Computational Linguistics: ACL (Findings of ACL)
- OpenAlex ID:https://openalex.org/W4402670146
- DOI:https://doi.org/10.18653/v1/2024.findings-acl.624
- arXiv:待核验
- 检索主题:memory-evaluation
- OpenAlex 引用数快照:670(2026-11-12)
摘要线索
Recent work has embodied LLMs as agents, allowing them to access tools, perform actions, and interact with external content (e.g., emails or websites).However, external content introduces the risk of indirect prompt injection (IPI) attacks, where malicious instructions are embedded within the content processed by LLMs, aiming to manipulate these agents into executing detrimental actions against users.Given the potentially severe consequences of such attacks, establishing benchmarks to assess and mitigate these risks is imperative.In this work, we introduce INJECAGENT, a benchmark designed to assess the vulnerability of tool-integrated LLM agents to IPI attacks.INJECAGENT comprises 1,054 test cases covering 17 different user tools and 62 attacker tools.We categorize attack intentions into two primary types: direct harm to users and exfiltration of private data.We evaluate 30 different LLM agents and show that agents are vulnerable to IPI attacks, with ReAct-prompted GPT-4 vulnerable to attacks 24% of the time.Further investigation into an enhanced setting, where the attacker instructions are reinforced with a hacking prompt, shows additional increases in success rates, nearly doubling the attack success rate on the ReAct-prompted GPT-4.Our findings raise questions about the widespread deployment of LLM Agents.
核验与筛选
- 当前状态:待筛选、去重和一手来源核验。
- OpenAlex 元数据和引用数只用于发现,不作为正式引文或质量判断。
- 记录正式版本、venue、方法细节、实验协议和局限后,才迁入稳定论文卡片。