Short-length Adversarial Training Helps LLMs Defend Long-length Jailbreak Attacks: Theoretical and Empirical Evidence - researchr publication authors

researchr

You are not signed in
Sign in
Sign up

Shaopeng Fu, Liang Ding, Jingfeng Zhang, Di Wang 0015. Short-length Adversarial Training Helps LLMs Defend Long-length Jailbreak Attacks: Theoretical and Empirical Evidence. 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 'Shaopeng Fu' in GoogleThis author has not been identified. Look up 'Liang Ding' in GoogleThis author has not been identified. Look up 'Jingfeng Zhang' in GoogleThis author has not been identified. Look up 'Di Wang 0015' in Google

runs on WebDSL