most citedMultiBreak: A Scalable and Diverse Multi-turn Jailbreak Benchmark for Evaluating LLM Safety

1 citations · 1 across the 3 of their papers we have counts for

collaborators

8 papers

cs.CR2026

Jailbreak susceptibility prediction and mitigation via the behavioral geometry of models

Hayden Helm, Xiaodong Liu, Weiwei Yang

Evaluating and mitigating a generative system's susceptibility to jailbreak attacks is critical to its safe deployment. Given the number of deployable systems, full per-configurati…

cs.AI2026

Agentic-imodels: Evolving agentic interpretability tools via autoresearch

Chandan Singh, Yan Shuo Tan, Weijia Xu +4

Agentic data science (ADS) systems are rapidly improving their capability to autonomously analyze, fit, and interpret data, potentially moving towards a future where agents conduct…

cs.CL20261 cited

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…

cs.AI2026

Statistical Estimation of Adversarial Risk in Large Language Models under Best-of-N Sampling

Mingqian Feng, Xiaodong Liu, Weiwei Yang +3

Large Language Models (LLMs) are typically evaluated for safety under single-shot or low-budget adversarial prompting, which underestimates real-world risk. In practice, attackers…

cs.CL2026

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…

cs.CL2025

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…