y0news
AnalyticsDigestsSourcesTopicsRSSAICrypto

#jailbreak-research News & Analysis

2 articles tagged with #jailbreak-research. AI-curated summaries with sentiment analysis and key takeaways from 50+ sources.

2 articles
AIBearisharXiv – CS AI · Jun 197/10
🧠

What Do Safety-Aligned LLMs Learn From Mixed Compliance Demonstrations?

Researchers analyzed how large language models interpret mixed compliance demonstrations—combining benign and harmful requests with helpful responses—revealing that demonstration composition critically affects model behavior. The study shows that benign demonstrations can either reduce or increase harmful compliance depending on the model, with preference optimization during training and demonstration ordering playing crucial roles in preventing jailbreaks.

AINeutralarXiv – CS AI · May 46/10
🧠

Minimal, Local, Causal Explanations for Jailbreak Success in Large Language Models

Researchers introduce LOCA, a method for identifying why specific jailbreak attacks succeed against safety-trained LLMs by pinpointing minimal, causal changes in intermediate representations. The approach provides local explanations for individual jailbreak instances rather than global theories, achieving refusal induction with an average of six interpretable changes compared to prior methods requiring 20+.

🧠 Llama