Organization
School of Computing Assistant Professor
Title
Assistant Professor
Homepage
External link
WEN RUI
Research Areas
-
Informatics / Information security
-
Informatics / Intelligent informatics
Papers
-
BadBone: Backdoor Attacks Against Backbone Models in Visual Prompt Learning Reviewed International coauthorship
Ziqing Yang, Rui Wen, Xinlei He, Yun Shen, Michael Backes, Yang Zhang
IEEE Transactions on Information Forensics and Security 2026.6
-
SL-CBM: Enhancing Concept Bottleneck Models with Semantic Locality for Better Interpretability Reviewed International coauthorship
Hanwei Zhang, Luo Cheng, Rui Wen, Yang Zhang, Lijun Zhang, Holger Hermanns
Proceedings of the AAAI Conference on Artificial Intelligence 40 ( 44 ) 38093 - 38101 2026.3
-
Inheritance Knows No Modality: How Jailbreak Vulnerabilities Propagate from Pretrained LLMs to Finetuned LLMs and VLMs
Yixin Tan, Zhe Yu, Jiayang Liu, Rui Wen, Jun Sakuma
2026
-
SoK: Data Reconstruction Attacks Against Machine Learning Models: Definition, Metrics, and Benchmark Reviewed International coauthorship International journal
Rui Wen, Yiyong Liu, Michael Backes, Yang Zhang
34rd USENIX Security Symposium 2025.8
-
Understanding Data Importance in Machine Learning Attacks: Does Valuable Data Pose Greater Harm? Reviewed International coauthorship International journal
Rui Wen 0002, Michael Backes 0001, Yang Zhang 0016
NDSS 2025.2
-
Peering Behind the Shield: Guardrail Identification in Large Language Models.
Ziqing Yang 0002, Yixin Wu 0001, Rui Wen 0002, Michael Backes 0001, Yang Zhang 0016
CoRR abs/2502.01241 2025.2
-
Dataset and Lessons Learned from the 2024 SaTML LLM Capture-the-Flag Competition. Reviewed International coauthorship International journal
Edoardo Debenedetti, Javier Rando, Daniel Paleka, Silaghi Fineas Florin, Dragos Albastroiu, Niv Cohen, Yuval Lemberg, Reshmi Ghosh, Rui Wen 0002, Ahmed Salem 0001, Giovanni Cherubin, Santiago Zanella-Béguelin, Robin Schmid, Victor Klemm, Takahiro Miki, Chenhao Li, Stefan Kraft, Mario Fritz, Florian Tramèr, Sahar Abdelnabi, Lea Schönherr
NeurIPS 2024.12
-
Membership Inference Attacks Against In-Context Learning. Reviewed International coauthorship International journal
Rui Wen 0002, Zheng Li 0023, Michael Backes 0001, Yang Zhang 0016
CCS 3481 - 3495 2024.10
-
Instruction Backdoor Attacks Against Customized LLMs. Reviewed International coauthorship International journal
Rui Zhang 0086, Hongwei Li 0001, Rui Wen 0002, Wenbo Jiang 0001, Yuan Zhang 0006, Michael Backes 0001, Yun Shen, Yang Zhang 0016
33rd USENIX Security Symposium 2024.8
-
Quantifying Privacy Risks of Prompts in Visual Prompt Learning. Reviewed International coauthorship International journal
Yixin Wu 0001, Rui Wen 0002, Michael Backes 0001, Pascal Berrang, Mathias Humbert, Yun Shen, Yang Zhang 0016
33rd USENIX Security Symposium 2024.8
-
Games and Beyond: Analyzing the Bullet Chats of Esports Livestreaming. Reviewed International coauthorship International journal
Yukun Jiang 0001, Xinyue Shen 0001, Rui Wen 0002, Zeyang Sha, Junjie Chu, Yugeng Liu, Michael Backes 0001, Yang Zhang 0016
Proceedings of the Eighteenth International AAAI Conference on Web and Social Media(ICWSM) 761 - 773 2024.6
-
Generated Distributions Are All You Need for Membership Inference Attacks Against Generative Models. Reviewed International coauthorship International journal
Minxing Zhang, Ning Yu 0006, Rui Wen 0002, Michael Backes 0001, Yang Zhang 0016
IEEE/CVF Winter Conference on Applications of Computer Vision(WACV) 4827 - 4837 2024.1
-
Efficient Data-Free Model Stealing with Label Diversity.
Yiyong Liu, Rui Wen 0002, Michael Backes 0001, Yang Zhang 0016
CoRR abs/2404.00108 2024
-
Is Adversarial Training Really a Silver Bullet for Mitigating Data Poisoning? Reviewed International coauthorship International journal
Rui Wen 0002, Zhengyu Zhao 0001, Zhuoran Liu 0001, Michael Backes 0001, Tianhao Wang 0001, Yang Zhang 0016
The Eleventh International Conference on Learning Representations(ICLR) 2023.5
-
Rui Wen 0002, Tianhao Wang 0001, Michael Backes 0001, Yang Zhang 0016, Ahmed Salem 0001
CoRR abs/2310.11397 2023
-
ML-Doctor: Holistic Risk Assessment of Inference Attacks Against Machine Learning Models. Reviewed International coauthorship International journal
Yugeng Liu, Rui Wen 0002, Xinlei He 0001, Ahmed Salem 0001, Zhikun Zhang 0001, Michael Backes 0001, Emiliano De Cristofaro, Mario Fritz, Yang Zhang 0016
31st USENIX Security Symposium 4525 - 4542 2022.8
-
Dynamic Backdoor Attacks Against Machine Learning Models. Reviewed International coauthorship International journal
Ahmed Salem 0001, Rui Wen 0002, Michael Backes 0001, Shiqing Ma, Yang Zhang 0016
7th IEEE European Symposium on Security and Privacy(EuroS&P) 703 - 718 2022.6
-
Node-Level Membership Inference Attacks Against Graph Neural Networks.
Xinlei He 0001, Rui Wen 0002, Yixin Wu 0001, Michael Backes 0001, Yun Shen, Yang Zhang 0016
CoRR abs/2102.05429 2021
-
LEAF: A Faster Secure Search Algorithm via Localization, Extraction, and Reconstruction. Reviewed International coauthorship International journal
Rui Wen 0002, Yu Yu 0001, Xiang Xie, Yang Zhang 0016
CCS '20: 2020 ACM SIGSAC Conference on Computer and Communications Security(CCS) 1219 - 1232 2020.11
Awards
-
Encouragement Award
2025.10 Pattern Enhanced Multi-Turn Jailbreaking: Exploiting Structural Vulnerabilities in LLM
Ragib Amin Nihal, Rui Wen, Kazuhiro Nakadai, Jun Sakuma
-
2nd place at Large Language Model Capture-the-Flag (LLM CTF) Competition
2024.3
Research Projects
-
Beyond One-Size-Fits-All: Sample-Level Vulnerability as a Foundation for Advanced ML Security
Grant number：26K21215 2026.4 - 2029.3
日本学術振興会 科学研究費助成事業 若手研究
Wen Rui
Grant amount：\4550000 （ Direct Cost: \3500000 、 Indirect Cost：\1050000 ）