Attractive Metadata Attack: Inducing LLM Agents to Invoke Malicious Tools - researchr publication authors

researchr

You are not signed in
Sign in
Sign up

Kanghua Mo, Li Hu, Yucheng Long, Zhihao Li. Attractive Metadata Attack: Inducing LLM Agents to Invoke Malicious Tools. In Danielle Belgrave, Cheng Zhang 0005, Laura N. Montoya, Hsuan-Tien Lin, Razvan Pascanu, Piotr Koniusz, Marzyeh Ghassemi, Nancy Chen, Iván Vladimir Meza Ruíz, Arturo Loaiza-Bonilla, editors, Advances in Neural Information Processing Systems 38: Annual Conference on Neural Information Processing Systems 2025, NeurIPS 2025, San Diago, CA, USA, December 2-7, 2025 / Mexico City, Mexico, November 30 - December 5, 2025. 2025. [doi]

This author has not been identified. Look up 'Kanghua Mo' in GoogleThis author has not been identified. Look up 'Li Hu' in GoogleThis author has not been identified. Look up 'Yucheng Long' in GoogleThis author has not been identified. Look up 'Zhihao Li' in Google

runs on WebDSL