New D-Judge defense disrupts LLM jailbreaks via output rewriting

Researchers have developed a new defense mechanism called D-Judge to counter multi-turn jailbreak attacks on large language models. These attacks use feedback from auxiliary judge models to iteratively refine prompts towards harmful goals. D-Judge works by rewriting the victim LLM's responses before they are evaluated by the attacker's judge, thus misaligning the feedback signal without altering the response's meaning. This strategy derails the prompt-refinement process, leading to improved safety on benchmarks like HarmBench while maintaining performance on benign tasks. AI

IMPACT Introduces a novel defense against sophisticated multi-turn jailbreaks, potentially enhancing LLM safety and reliability.

RANK_REASON The cluster contains a research paper detailing a novel defense mechanism for LLM safety. [lever_c_demoted from research: ic=1 ai=1.0]

Read on arXiv cs.AI →

• D-Judge
• HarmBench
• large language model
• N. Benjamin Erichson

• safety
• paper

AI-generated summary · Google Gemini · from 1 sources. How we write summaries →