MixAT: Combining Continuous and Discrete Adversarial Training for LLMs
机构 * INSAIT, Sofia University "St. Kliment Ohridski"(INSAIT,索菲亚大学"圣克莱孟·奥赫里迪斯基") ; ETH Zurich(苏黎世联邦理工学院) ; ELTE Eötvös Loránd University, Budapest, Hungary(ELTE 爱斯特霍特·洛兰德大学,布达佩斯,匈牙利)
专题命中 越狱攻击 :alignment(abstract);safety(abstract);分类 cs.AI、cs.LG
Comments Published at 39th Conference on Neural Information Processing Systems (NeurIPS 2025)