Han Sun
Titles as the sources gave them. In 1 entry, with 0 checked quotations.
In the Base
Every entry they appear in.
Budgeted Attack Scheduling for LLM Red-Teaming: The Roles of Static Priors, Semantic Guidance, and Online Feedback
According to the abstract, Zhicheng Fang, Han Sun, Jiachen Lei and colleagues study how to prioritize jailbreak attacks under a limited attempt budget in red-teaming. They compare three signals, historical success rates, semantic guidance from LLMs and online feedback, in four scheduling strategies across three victim models and three defenses.