Benign Samples Matter! Fine-tuning On Outlier Benign Samples Severely Breaks Safety.
Zihan Guan, Mengxuan Hu, Ronghang Zhu, Sheng Li, Anil Vullikanti
Browse the full ICML paper archive.
Zihan Guan, Mengxuan Hu, Ronghang Zhu, Sheng Li, Anil Vullikanti
Browse the full ICML paper archive.