arXiv · cs.AI · Shiyu Kan (Shanghai Jiao Tong University, Shanghai, China), Yue Qi (Shanghai Jiao Tong University, Shanghai, China), Yufei Han (Inria, Rennes, France), Xinjian Luo (Shanghai Jiao Tong University, Shanghai, China), Guojun Xiong (Shanghai Jiao Tong University, Shanghai, China), Xiaofeng Gao (Shanghai Jiao Tong University, Shanghai, China) · 8 小时前模型评分63
上海交大等提出 ETUDE 攻击：大语言模型（LLM，Large Language Model） 智能体工具更新后未重新验证带来供应链风险
Beyond Prompt Injection: The Tool Update Gap in LLM Agent Security
导读
上海交通大学与 Inria 的研究者提出 ETUDE（Exploiting Tool Updates for Direct Execution）攻击，把恶意功能嵌入原本无害工具的更新中，同时保留其正常功能。
分类置信度
中 · 待人工复核
- 只有单一媒体来源，需要人工复核。
来源级别：媒体与个人
事件类型：研究发布
证据摘录
- “we introduce ETUDE (Exploiting Tool Updates for Direct Execution), an attack that embeds malicious functionality into updates of initially benign tools to produce compromised tools, while preserving their legitimate tool functionality.”
- “The results show that ETUDE achieves a 97.6% ASR while maintaining a 95.9% legitimate task completion rate.”
- “We evaluate ETUDE across three representative attack workloads and seven widely used commercial and open-source agentic frameworks, including Gemini CLI, Codex CLI, and Claude Code.”
来源：arXiv · cs.AI · arxiv.org