default search action
Google
Google Scholar
Semantic Scholar
Internet Archive Scholar
CiteSeerX
ORCIDWai Man Si
Person information
Refine list
refinements active!
zoomed in on ?? of ?? records
view refined list in
2020 – today
- 2026
[c6]Wai Man Si, Mingjie Li, Michael Backes, Yang Zhang:
Pruning Unsafe Tickets: A Resource-Efficient Framework for Safer and More Robust LLMs. ACL (1) 2026: 26285-26302- [c5]Mingjie Li, Wai Man Si, Michael Backes, Yang Zhang:
Reward Yourself: Efficient Self Rewards for Trustworthy Sampling. ACL (Findings) 2026: 31070-31086 - [i11]Mingjie Li, Wai Man Si, Michael Backes, Yang Zhang, Yisen Wang:
Finding and Reactivating Post-Trained LLMs' Hidden Safety Mechanisms. CoRR abs/2604.00012 (2026) - [i10]Wai Man Si, Mingjie Li, Michael Backes, Yang Zhang:
Pruning Unsafe Tickets: A Resource-Efficient Framework for Safer and More Robust LLMs. CoRR abs/2604.15780 (2026) - [i9]Wai Man Si, Mingjie Li, Michael Backes, Yang Zhang:
A Systematic Study of Training-Free Methods for Trustworthy Large Language Models. CoRR abs/2604.15789 (2026) - 2025
- [c4]Mingjie Li, Wai Man Si, Michael Backes, Yang Zhang, Yisen Wang:
SaLoRA: Safety-Alignment Preserved Low-Rank Adaptation. ICLR 2025 - [i8]Mingjie Li, Wai Man Si, Michael Backes, Yang Zhang, Yisen Wang:
SaLoRA: Safety-Alignment Preserved Low-Rank Adaptation. CoRR abs/2501.01765 (2025) - [i7]Wai Man Si, Mingjie Li, Michael Backes, Yang Zhang:
Excessive Reasoning Attack on Reasoning LLMs. CoRR abs/2506.14374 (2025) - 2024
- [i6]Wai Man Si, Michael Backes, Yang Zhang
:
ICLGuard: Controlling In-Context Learning Behavior for Applicability Authorization. CoRR abs/2407.06955 (2024) - 2023
- [c3]Wai Man Si, Michael Backes, Yang Zhang, Ahmed Salem:
Two-in-One: A Model Hijacking Attack Against Text Generation Models. USENIX Security Symposium 2023: 2223-2240 - [i5]Wai Man Si, Michael Backes, Yang Zhang, Ahmed Salem:
Two-in-One: A Model Hijacking Attack Against Text Generation Models. CoRR abs/2305.07406 (2023) - [i4]Wai Man Si, Michael Backes, Yang Zhang:
Mondrian: Prompt Abstraction Attack Against Large Language Models for Cheaper API Pricing. CoRR abs/2308.03558 (2023) - [i3]Boyang Zhang, Xinyue Shen, Wai Man Si, Zeyang Sha, Zeyuan Chen, Ahmed Salem, Yun Shen, Michael Backes, Yang Zhang:
Comprehensive Assessment of Toxicity in ChatGPT. CoRR abs/2311.14685 (2023) - 2022
- [c2]Wai Man Si, Michael Backes, Jeremy Blackburn, Emiliano De Cristofaro, Gianluca Stringhini, Savvas Zannettou, Yang Zhang:
Why So Toxic?: Measuring and Triggering Toxic Behavior in Open-Domain Chatbots. CCS 2022: 2659-2673 - [i2]Wai Man Si, Michael Backes, Jeremy Blackburn, Emiliano De Cristofaro, Gianluca Stringhini, Savvas Zannettou, Yang Zhang:
Why So Toxic? Measuring and Triggering Toxic Behavior in Open-Domain Chatbots. CoRR abs/2209.03463 (2022) - 2021
- [c1]Wai Man Si, Prithviraj Ammanabrolu, Mark O. Riedl:
Telling Stories through Multi-User Dialogue by Modeling Character Relations. SIGDIAL 2021: 269-275 - [i1]Wai Man Si, Prithviraj Ammanabrolu, Mark O. Riedl:
Telling Stories through Multi-User Dialogue by Modeling Character Relations. CoRR abs/2105.15054 (2021)
Coauthor Index
manage site settings
To protect your privacy, all features that rely on external API calls from your browser are turned off by default. You need to opt-in for them to become active. All settings here will be stored as cookies with your web browser. For more information see our F.A.Q.
Unpaywalled article links
Add open access links from 
to the list of external document links (if available).
Privacy notice: By enabling the option above, your browser will contact the API of unpaywall.org to load hyperlinks to open access articles. Although we do not have any reason to believe that your call will be tracked, we do not have any control over how the remote server uses your data. So please proceed with care and consider checking the Unpaywall privacy policy.
Archived links via Wayback Machine
For web page which are no longer available, try to retrieve content from the 
of the Internet Archive (if available).
Privacy notice: By enabling the option above, your browser will contact the API of archive.org to check for archived content of web pages that are no longer available. Although we do not have any reason to believe that your call will be tracked, we do not have any control over how the remote server uses your data. So please proceed with care and consider checking the Internet Archive privacy policy.
Reference lists
Add a list of references from 
, 
, and 
to record detail pages.
load references from crossref.org and opencitations.net
Privacy notice: By enabling the option above, your browser will contact the APIs of crossref.org, opencitations.net, and semanticscholar.org to load article reference information. Although we do not have any reason to believe that your call will be tracked, we do not have any control over how the remote server uses your data. So please proceed with care and consider checking the Crossref privacy policy and the OpenCitations privacy policy, as well as the AI2 Privacy Policy covering Semantic Scholar.
Citation data
Add a list of citing articles from and to record detail pages.
load citations from opencitations.net
Privacy notice: By enabling the option above, your browser will contact the API of opencitations.net and semanticscholar.org to load citation information. Although we do not have any reason to believe that your call will be tracked, we do not have any control over how the remote server uses your data. So please proceed with care and consider checking the OpenCitations privacy policy as well as the AI2 Privacy Policy covering Semantic Scholar.
OpenAlex data
Load additional information about publications from 
.
Privacy notice: By enabling the option above, your browser will contact the API of openalex.org to load additional information. Although we do not have any reason to believe that your call will be tracked, we do not have any control over how the remote server uses your data. So please proceed with care and consider checking the information given by OpenAlex.
last updated on 2026-07-28 00:45 CEST by the dblp team
all metadata released as open data under CC0 1.0 license
see also: Terms of Use | Privacy Policy | Imprint
dblp was originally created in 1993 at:
since 2018, dblp has been operated, funded, and maintained by:
Schloss Dagstuhl - Leibniz Center for Informatics is a member of the Leibniz Association and is funded by the federal government of Germany and the states of Germany, especially Saarland and Rhineland‑Palatinate.
