Yukai Zhou
Yukai Zhou — researcher or builder tracked in the Angestrom contributor network.
Papers · 2
How Jailbreak Attacks Inform Safety Alignment: A Defender-Centric, Shapley-Based Evaluation of Jailbreak Contributions
Jailbreak attacks on large language models are usually evaluated by attacker-centric metrics such as attack success rate (ASR), yet an attack that breaks a model is not necessarily useful for improving its safety. We propose a defender-centric view of jailbreak evaluation, where attacks are evaluated by the downstream safety improvements they enable when used as red-teaming data for safety training. Building on this view, we introduce A-MESS (Minimal Effective Attack-Subset Selection), a setting-agnostic framework for attributing and selecting jailbreak attacks from black-box subset utility ob
DSPrompt: Dynamic Soft Prompt Defense Against M-RAG Corruption
Multimodal Retrieval Augmented Generation (M-RAG) is increasingly vulnerable to adversarial attacks where malicious data are crafted to produce embeddings that align with benign entries in the vector space, deceiving retrieval and inducing harmful outputs. Existing defenses primarily operate at query time, relying on auxiliary detectors, similarity re-ranking, or feature-consistency checks. However, these approaches suffer from non-trivial inference overhead, generalize poorly to unseen attack strategies, and often assume specific attack distributions. To address this, we propose DSPrompt, a D