Wai Man Si

According to our database, Wai Man Si authored at least 11 papers between 2021 and 2026.

Collaborative distances:

• Dijkstra number of four.
• Erdős number of four.

2026

A Systematic Study of Training-Free Methods for Trustworthy Large Language Models.

Wai Man Si, Mingjie Li, Michael Backes, Yang Zhang

CoRR, April, 2026

Finding and Reactivating Post-Trained LLMs' Hidden Safety Mechanisms.

Mingjie Li, Wai Man Si, Michael Backes, Yang Zhang, Yisen Wang

CoRR, April, 2026

Pruning Unsafe Tickets: A Resource-Efficient Framework for Safer and More Robust LLMs.

Wai Man Si, Mingjie Li, Michael Backes, Yang Zhang

Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), 2026

2025

Excessive Reasoning Attack on Reasoning LLMs.

Wai Man Si, Mingjie Li, Michael Backes, Yang Zhang

CoRR, June, 2025

SaLoRA: Safety-Alignment Preserved Low-Rank Adaptation.

Mingjie Li, Wai Man Si, Michael Backes, Yang Zhang, Yisen Wang

Proceedings of the Thirteenth International Conference on Learning Representations, 2025

2024

ICLGuard: Controlling In-Context Learning Behavior for Applicability Authorization.

Wai Man Si, Michael Backes, Yang Zhang

CoRR, 2024

2023

Comprehensive Assessment of Toxicity in ChatGPT.

Boyang Zhang, Xinyue Shen, Wai Man Si, Zeyang Sha, Zeyuan Chen, Ahmed Salem, Yun Shen, Michael Backes, Yang Zhang

CoRR, 2023

Mondrian: Prompt Abstraction Attack Against Large Language Models for Cheaper API Pricing.

Wai Man Si, Michael Backes, Yang Zhang

CoRR, 2023

Two-in-One: A Model Hijacking Attack Against Text Generation Models.

Wai Man Si, Michael Backes, Yang Zhang, Ahmed Salem

Proceedings of the 32nd USENIX Security Symposium, 2023

2022

Why So Toxic?: Measuring and Triggering Toxic Behavior in Open-Domain Chatbots.

Wai Man Si, Michael Backes, Jeremy Blackburn, Emiliano De Cristofaro, Gianluca Stringhini, Savvas Zannettou, Yang Zhang

Proceedings of the 2022 ACM SIGSAC Conference on Computer and Communications Security, 2022

2021

Telling Stories through Multi-User Dialogue by Modeling Character Relations.

Wai Man Si, Prithviraj Ammanabrolu, Mark O. Riedl

Proceedings of the 22nd Annual Meeting of the Special Interest Group on Discourse and Dialogue, 2021