259 citations · 1.2k across the 51 of their papers we have counts for
56 papers
Multiple Turns, Short Horizons: Measuring Effective-Horizon Compression in Jailbreaks
Zhipeng Wei, Michael Lee, N. Benjamin Erichson
Multi-turn jailbreaks use feedback from a victim large language model to adapt their queries over several turns. However, once an effective trajectory has been found, it is unclear…
Divide and Inject: Can Agents Reconstruct an Indirect Prompt Injection from Fragments?
Michael Lee, Zhipeng Wei, Yue Dong +1
Agentic systems are now being widely used to orchestrate tools and reason over long contexts. However, the improving capabilities of the large language models powering these agents…
D-Judge: Disrupting Multi-Turn Jailbreaks using Semantics-Preserving Output Rewriting
Huanli Gong, Zhipeng Wei, Yu Fu +4
Multi-turn jailbreak attacks pose a growing threat to large language model (LLM) safety because they exploit feedback from auxiliary judge models to iteratively refine prompts towa…
Reducing the Safety Tax in LLM Safety Alignment with On-Policy Self-Distillation
Yu Fu, Longxuan Yu, Haz Sameen Shahgir +4
Safety alignment often improves robustness to harmful queries at the cost of reasoning ability, a tradeoff known as the safety tax. A common cause is distributional mismatch: super…
Sharpen Your Flow: Sharpness-Aware Sampling for Flow Matching
Aditi Gupta, Soon Hoe Lim, Annan Yu +1
Flow matching models generate samples by numerically integrating a learned velocity field, with each integration step requiring a neural network evaluation. Fast generation therefo…
MT-JailBench: A Modular Benchmark for Understanding Multi-Turn Jailbreak Attacks
Xinkai Zhang, Zhipeng Wei, Huanli Gong +4
Multi-turn jailbreaks exploit the ability of large language models to accumulate and act on conversational context. Instead of stating a harmful request directly, an attacker can g…