Defending large language models against jailbreak attacks via layer-specific editing

• Main Authors: ZHAO, Wei, LI, Zhe, LI, Yige, SUN, Jun
• Format: text
• Language: English
• Published: Institutional Knowledge at Singapore Management University 2024
• Subjects: Software Engineering
• Online Access: https://ink.library.smu.edu.sg/sis_research/9832; https://ink.library.smu.edu.sg/context/sis_research/article/10832/viewcontent/2024.findings_emnlp.293.pdf
• Institution: Singapore Management University

Large language models (LLMs) are increasingly being adopted in a wide range of realworld applications. Despite their impressive performance, recent studies have shown that LLMs are vulnerable to deliberately crafted adversarial prompts even when aligned via Reinforcement Learning from Human Feedback...