Hugging Face Trending Papers

Fair ASR: Re-Evaluating Black-Box Jailbreaks under Shared Target-Call Budgets

Read the original on Hugging Face Trending Papers →

Reliable jailbreak evaluation is essential for assessing LLM safety, but most existing studies rely solely on attack success rate (ASR) without accounting for its dependence on attack budgets, resulting in unfair comparisons across methods. Existing compute-aware evaluations reduce heterogeneous resources into FLOPs, which is difficult to estimate for black-box models and fails to capture resource-specific constraints.

Summary generated by The Flow from the publisher's feed. The full article lives at Hugging Face Trending Papers.

arXiv AI
23h ago

Fair ASR: Re-Evaluating Black-Box Jailbreaks under Shared Target-Call Budgets

arXiv:2608. 17360v1 Announce Type: cross Abstract: Reliable jailbreak evaluation is essential for assessing LLM safety, but most existing studies rely solely on attack success rate (ASR) without accounting for its dependence on attack budgets, resulting in unfair comparisons across methods.

By Zhida He, Xiaoyu Wen, Han Qi, Ziyuan Zhou, Peng Yu, Jiajia Li, Chaochao Lu, Qiaosheng Zhang