Showing cs.CRShow all
2 papers · 1 filter
cs.CR2026
CoLA: A Choice Leakage Attack Framework to Expose Privacy Risks in Subset Training
Qi Li, Cheng-Long Wang, Yinzhi Cao +1
Training models on a carefully chosen portion of data rather than the full dataset is now a standard preprocess for modern ML. From vision coreset selection to large-scale filterin…
cs.CR2026
Accelerating Suffix Jailbreak attacks with Prefix-Shared KV-cache
Xinhai Wang, Shaopeng Fu, Shu Yang +3
Suffix jailbreak attacks serve as a systematic method for red-teaming Large Language Models (LLMs) but suffer from prohibitive computational costs, as a large number of candidate s…