1 citations · 1 across the 3 of their papers we have counts for
5 papers · 1 filter
MultiBreak: A Scalable and Diverse Multi-turn Jailbreak Benchmark for Evaluating LLM Safety
Jialin Song, Xiaodong Liu, Weiwei Yang +4
We present MultiBreak, a scalable and diverse multi-turn jailbreak benchmark to evaluate large language model (LLM) safety. Multi-turn jailbreaks mimic natural conversational setti…
SEMA: Simple yet Effective Learning for Multi-Turn Jailbreak Attacks
Mingqian Feng, Xiaodong Liu, Weiwei Yang +4
Multi-turn jailbreaks capture the real threat model for safety-aligned chatbots, where single-turn attacks are merely a special case. Yet existing approaches break under exploratio…
Iterative Self-Tuning LLMs for Enhanced Jailbreaking Capabilities
Chung-En Sun, Xiaodong Liu, Weiwei Yang +5
Recent research has shown that Large Language Models (LLMs) are vulnerable to automated jailbreak attacks, where adversarial suffixes crafted by algorithms appended to harmful quer…
Interpretable Next-token Prediction via the Generalized Induction Head
Eunji Kim, Sriya Mantena, Weiwei Yang +3
While large transformer models excel in predictive performance, their lack of interpretability restricts their usefulness in high-stakes domains. To remedy this, we propose the Gen…
NeurIPS 2023 LLM Efficiency Fine-tuning Competition
Mark Saroufim, Yotam Perlitz, Leshem Choshen +11
Our analysis of the NeurIPS 2023 large language model (LLM) fine-tuning competition revealed the following trend: top-performing models exhibit significant overfitting on benchmark…