publications

2025

1. NDSS

   Understanding Data Importance in Machine Learning Attacks: Does Valuable Data Pose Greater Harm?

   Wen, Rui, Backes, Michael, and Zhang, Yang

   In 31st Annual Network and Distributed System Security Symposium (NDSS) 2025

   Bib HTML

   @inproceedings{WBZ25,
     author = {Wen, Rui and Backes, Michael and Zhang, Yang},
     title = {{Understanding Data Importance in Machine Learning Attacks: Does Valuable Data Pose Greater Harm?}},
     booktitle = {{31st Annual Network and Distributed System Security Symposium (NDSS)}},
     publisher = {The Internet Society},
     year = {2025},
   }

2024

1. CCS

   Membership Inference Attacks Against In-Context Learning

   Wen, Rui, Li, Zheng, Backes, Michael, and Zhang, Yang

   In ACM SIGSAC Conference on Computer and Communications Security (CCS) 2024

   Bib HTML

   @inproceedings{WLBZ24,
     author = {Wen, Rui and Li, Zheng and Backes, Michael and Zhang, Yang},
     title = {{Membership Inference Attacks Against In-Context Learning}},
     booktitle = {{ACM SIGSAC Conference on Computer and Communications Security (CCS)}},
     publisher = {ACM},
     year = {2024},
   }

2. Security

   Instruction Backdoor Attacks Against Customized LLMs

   Zhang, Rui, Li, Hongwei,  Wen, Rui, Jiang, Wenbo, Zhang, Yuan, Backes, Michael, Shen, Yun, and Zhang, Yang

   In USENIX Security Symposium (USENIX Security) 2024

   Bib HTML

   @inproceedings{ZLWJZBSZ24,
     author = {Zhang, Rui and Li, Hongwei and Wen, Rui and Jiang, Wenbo and Zhang, Yuan and Backes, Michael and Shen, Yun and Zhang, Yang},
     title = {Instruction Backdoor Attacks Against Customized LLMs},
     booktitle = {{USENIX Security Symposium (USENIX Security)}},
     publisher = {USENIX},
     year = {2024},
   }

3. Security

   Quantifying Privacy Risks of Prompts in Visual Prompt Learning

   Wu, Yixin,  Wen, Rui, Backes, Michael, Berrang, Pascal, Humbert, Mathias, Shen, Yun, and Zhang, Yang

   In USENIX Security Symposium (USENIX Security) 2024

   Bib HTML

   @inproceedings{WWBBHSZ24,
     author = {Wu, Yixin and Wen, Rui and Backes, Michael and Berrang, Pascal and Humbert, Mathias and Shen, Yun and Zhang, Yang},
     title = {Quantifying Privacy Risks of Prompts in Visual Prompt Learning},
     booktitle = {{USENIX Security Symposium (USENIX Security)}},
     publisher = {USENIX},
     year = {2024},
   }

4. NeurIPS

   Dataset and Lessons Learned from the 2024 SaTML LLM Capture-the-Flag Competition

   Debenedetti, Edoardo, Rando, Javier, Paleka, Daniel, Florin, Silaghi Fineas, Albastroiu, Dragos, Cohen, Niv, Lemberg, Yuval, Ghosh, Reshmi,  Wen, Rui, Salem, Ahmed, Cherubin, Giovanni, Béguelin, Santiago Zanella, Schmid, Robin, Klemm, Victor, Miki, Takahiro, Li, Chenhao, Kraft, Stefan, Fritz, Mario, Tramèr, Florian, Abdelnabi, Sahar, and Schönherr, Lea

   In Annual Conference on Neural Information Processing Systems (NeurIPS) 2024

   Bib HTML

   @inproceedings{dataset,
     author = {Debenedetti, Edoardo and Rando, Javier and Paleka, Daniel and Florin, Silaghi Fineas and Albastroiu, Dragos and Cohen, Niv and Lemberg, Yuval and Ghosh, Reshmi and Wen, Rui and Salem, Ahmed and Cherubin, Giovanni and B{\'{e}}guelin, Santiago Zanella and Schmid, Robin and Klemm, Victor and Miki, Takahiro and Li, Chenhao and Kraft, Stefan and Fritz, Mario and Tram{\`{e}}r, Florian and Abdelnabi, Sahar and Sch{\"{o}}nherr, Lea},
     title = {Dataset and Lessons Learned from the 2024 SaTML LLM Capture-the-Flag
                     Competition},
     booktitle = {{Annual Conference on Neural Information Processing Systems (NeurIPS)}},
     publisher = {NeurIPS},
     year = {2024},
   }

5. ICWSM

   Games and Beyond: Analyzing the Bullet Chats of Esports Livestreaming

   Jiang, Yukun, Shen, Xinyue,  Wen, Rui, Sha, Zeyang, Chu, Junjie, Liu, Yugeng, Backes, Michael, and Zhang, Yang

   In Proceedings of the Eighteenth International AAAI Conference on Web and Social Media (ICWSM) 2024

   Bib HTML

   @inproceedings{JSWSCLBZ24,
     author = {Jiang, Yukun and Shen, Xinyue and Wen, Rui and Sha, Zeyang and Chu, Junjie and Liu, Yugeng and Backes, Michael and Zhang, Yang},
     title = {Games and Beyond: Analyzing the Bullet Chats of Esports Livestreaming},
     booktitle = {{Proceedings of the Eighteenth International AAAI Conference on Web and Social Media (ICWSM)}},
     publisher = {AAAI},
     year = {2024},
   }

6. WACV

   Generated Distributions Are All You Need for Membership Inference Attacks Against Generative Models

   Zhang, Minxing, Yu, Ning,  Wen, Rui, Backes, Michael, and Zhang, Yang

   In IEEE/CVF Winter Conference on Applications of Computer Vision (WACV) 2024

   Bib HTML

   @inproceedings{ZYWBZ24,
     author = {Zhang, Minxing and Yu, Ning and Wen, Rui and Backes, Michael and Zhang, Yang},
     title = {Generated Distributions Are All You Need for Membership Inference Attacks Against Generative Models},
     booktitle = {{IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}},
     publisher = {IEEE},
     year = {2024},
   }

2023

1. ICLR

   Is Adversarial Training Really a Silver Bullet for Mitigating Data Poisoning?

   Wen, Rui, Zhao, Zhengyu, Liu, Zhuoran, Backes, Michael, Wang, Tianhao, and Zhang, Yang

   In International Conference on Learning Representations (ICLR) 2023

   Bib HTML

   @inproceedings{WZLBWZ23,
     author = {Wen, Rui and Zhao, Zhengyu and Liu, Zhuoran and Backes, Michael and Wang, Tianhao and Zhang, Yang},
     title = {{Is Adversarial Training Really a Silver Bullet for Mitigating Data Poisoning?}},
     booktitle = {{International Conference on Learning Representations (ICLR)}},
     year = {2023},
   }

2. arXiv

   Last One Standing: A Comparative Analysis of Security and Privacy of Soft Prompt Tuning, LoRA, and In-Context Learning

   Wen, Rui, Wang, Tianhao, Backes, Michael, Zhang, Yang, and Salem, Ahmed

   CoRR abs/2310.11397 2023

   Bib HTML

   @article{WWBZS23,
     author = {Wen, Rui and Wang, Tianhao and Backes, Michael and Zhang, Yang and Salem, Ahmed},
     title = {{Last One Standing: A Comparative Analysis of Security and Privacy of Soft Prompt Tuning, LoRA, and In-Context Learning
     }},
     journal = {{CoRR abs/2310.11397}},
     year = {2023},
   }

2022

1. Security

   ML-Doctor: Holistic Risk Assessment of Inference Attacks Against Machine Learning Models

   Liu, Yugeng*,  Wen, Rui*, He, Xinlei, Salem, Ahmed, Zhang, Zhikun, Backes, Michael, Cristofaro, Emiliano De, Fritz, Mario, and Zhang, Yang (* Equal Contribution)

   In USENIX Security Symposium (USENIX Security) 2022

   Bib HTML

   @inproceedings{LWHSZBCFZ22,
     author = {Liu, Yugeng* and Wen, Rui* and He, Xinlei and Salem, Ahmed and Zhang, Zhikun and Backes, Michael and Cristofaro, Emiliano De and Fritz, Mario and Zhang, Yang (* Equal Contribution)},
     title = {{ML-Doctor: Holistic Risk Assessment of Inference Attacks Against Machine Learning Models}},
     booktitle = {{USENIX Security Symposium (USENIX Security)}},
     pages = {4525-4542},
     publisher = {USENIX},
     year = {2022},
   }

2. Euro S&P

   Dynamic Backdoor Attacks Against Machine Learning Models

   Salem, Ahmed*,  Wen, Rui*, Backes, Michael, Ma, Shiqing, and Zhang, Yang (* Equal Contribution)

   In IEEE European Symposium on Security and Privacy (Euro S&P) 2022

   Bib HTML

   @inproceedings{SWBMZ22,
     author = {Salem, Ahmed* and Wen, Rui* and Backes, Michael and Ma, Shiqing and Zhang, Yang (* Equal Contribution)},
     title = {{Dynamic Backdoor Attacks Against Machine Learning Models}},
     booktitle = {{IEEE European Symposium on Security and Privacy (Euro S\&P)}},
     pages = {703-718},
     publisher = {IEEE},
     year = {2022},
   }

2021

1. arXiv

   Node-Level Membership Inference Attacks Against Graph Neural Networks

   He, Xinlei,  Wen, Rui, Wu, Yixin, Backes, Michael, Shen, Yun, and Zhang, Yang

   CoRR abs/2102.05429 2021

   Bib HTML

   @article{HWWBSZ21,
     author = {He, Xinlei and Wen, Rui and Wu, Yixin and Backes, Michael and Shen, Yun and Zhang, Yang},
     title = {{Node-Level Membership Inference Attacks Against Graph Neural Networks}},
     journal = {{CoRR abs/2102.05429}},
     year = {2021},
   }

2020

1. CCS

   LEAF: A Faster Secure Search Algorithm via Localization, Extraction, and Reconstruction

   Wen, Rui, Yu, Yu, Xie, Xiang, and Zhang, Yang

   In ACM SIGSAC Conference on Computer and Communications Security (CCS) 2020

   Bib HTML

   @inproceedings{WYXZ20,
     author = {Wen, Rui and Yu, Yu and Xie, Xiang and Zhang, Yang},
     title = {{LEAF: A Faster Secure Search Algorithm via Localization, Extraction, and Reconstruction}},
     booktitle = {{ACM SIGSAC Conference on Computer and Communications Security (CCS)}},
     pages = {1219-1232},
     publisher = {ACM},
     year = {2020},
   }