Author

Shi-Liang Xiao

View on Semantic Scholar

2 papers indexed here

We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.

Not the right person? Other researchers publish under this name.

#natural language process... Open access Aug 2026

OASIS: Optimizing Attacker Sequences for Hard-Label Black-Box Text Attacks

Experiments across multiple datasets, victim models, and large language models show that OASIS consistently outperforms strong standalone baselines and simple manually constructed chains, suggesting that attacker composition is not merely an implementation choice, but a practical optimization target for improving hard-label black-box text attacks.

Qian Chen, Shi-Liang Xiao, Yu-Zhi Liang · International Conference on... · 0 citations

#machine learning Preprint Aug 2026

TACS: Trajectory-Aware Candidate Selection for LLM Jailbreak Suffix Optimization

TACS is proposed, a trajectory-aware candidate selection framework for jailbreak suffix optimization that augments per-step evaluation with a trajectory-aware proxy and stabilizes selection with reference-policy regularization and a discriminator-estimated chi-squared correction, encouraging choices that remain effective beyond the current step.

Shi-Liang Xiao · 0 citations