Showing cs.CLShow all
2 papers · 1 filter
cs.CL2026
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…
cs.CL2026
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…