4 papers
Breadth Beats Depth: Improving GCG-Based Jailbreak Optimization with Breadth-Oriented Suffix Search
Shiliang Xiao, Jingsong Wei, Yuzhi Liang +3
Optimization-based jailbreak attacks such as Greedy Coordinate Gradient (GCG) achieve strong effectiveness and transferability by optimizing adversarial suffixes on white-box sourc…
OASIS: Optimizing Attacker Sequences for Hard-Label Black-Box Text Attacks
Qian Chen, Shiliang Xiao, Yuzhi Liang
Different attack methods follow different search trajectories, they succeed on different subsets of samples, whereas existing hard-label black-box text attacks mainly focus on impr…
TACS: Trajectory-Aware Candidate Selection for LLM Jailbreak Suffix Optimization
Shiliang Xiao
Gradient-based jailbreak suffix optimization methods typically update the suffix by retaining the candidate with the lowest current loss. We show that this seemingly natural design…
PivotAttack: Rethinking the Search Trajectory in Hard-Label Text Attacks via Pivot Words
Yuzhi Liang, Shiliang Xiao, Jingsong Wei +2
Existing hard-label text attacks often rely on inefficient "outside-in" strategies that traverse vast search spaces. We propose PivotAttack, a query-efficient "inside-out" framewor…