作者位次 #4/11ICLR 2026Poster· Social Aspects / Trustworthy Machine Learning
Adversarial Déjà Vu: Jailbreak Dictionary Learning for Stronger Generalization to Unseen Attacks
Mahavir Dabas · Tran Huynh · Nikhil Billa · Jiachen (Tianhao) Wang · Peng Gao · Charith Peris · Yao Ma · Rahul Gupta · Ming Jin · Prateek Mittal · Ruoxi Jia