Forewarned is Forearmed: Pre-Synthesizing Jailbreak-like Instructions to Enhance LLM Safety Guardrail to Potential Attacks.
Sheng Liu, Qiang Sheng, Danding Wang, Yang Liu, Guang Yang, Juan Cao
Browse the full EMNLP paper archive.
Sheng Liu, Qiang Sheng, Danding Wang, Yang Liu, Guang Yang, Juan Cao
Browse the full EMNLP paper archive.