Sledovat
Wai Man Si
Wai Man Si
CISPA
E-mailová adresa ověřena na: cispa.de - Domovská stránka
Název
Citace
Citace
Rok
Why so toxic? measuring and triggering toxic behavior in open-domain chatbots
WM Si, M Backes, J Blackburn, E De Cristofaro, G Stringhini, S Zannettou, ...
CCS 2022, 2022
722022
Two-in-One: A Model Hijacking Attack Against Text Generation Models
WM Si, M Backes, Y Zhang, A Salem
USENIX 2023, 2023
172023
Telling Stories through Multi-User Dialogue by Modeling Character Relations
WM Si, P Ammanabrolu, MO Riedl
SIGDIAL 2021, 2021
132021
Mondrian: Prompt abstraction attack against large language models for cheaper api pricing
WM Si, M Backes, Y Zhang
arXiv preprint arXiv:2308.03558, 2023
62023
Comprehensive assessment of toxicity in ChatGPT
B Zhang, X Shen, WM Si, Z Sha, Z Chen, A Salem, Y Shen, M Backes, ...
arXiv preprint arXiv:2311.14685, 2023
52023
SaLoRA: Safety-Alignment Preserved Low-Rank Adaptation
M Li, WM Si, M Backes, Y Zhang, Y Wang
ICLR 2025, 2025
12025
ICLGuard: Controlling In-Context Learning Behavior for Applicability Authorization
WM Si, M Backes, Y Zhang
arXiv preprint arXiv:2407.06955, 2024
12024
Boosting Variational Generative Model via Condition Enhancing and Lexical-Editing
Z Tao, W Si, J Li, D Zhao, R Yan
PRICAI 2019, 2019
2019
Systém momentálně nemůže danou operaci provést. Zkuste to znovu později.
Články 1–8