About Me

I received my PhD from University of Chicago Computer Science. I was advised by Prof. Heather Zheng and Prof. Ben Zhao researching on machine learning security. I received my bachelor’s degrees in Computer Science and Mathematical Sciences with a minor in Computational Finance from Carnegie Mellon University in 2020. I received my master’s degree in Computer Science – Research Thesis from Carnegie Mellon University in 2021, jointly advised by Prof. Nihar Shah and Prof. Weina Wang.

Email: wenxind98 [at] gmail.com

Education

University of Chicago

• Ph.D. in Computer Science 2021–2026

Carnegie Mellon University

• M.S. in Computer Science – Research Thesis 2020–2021

• B.S. (Hons) in Computer Science 2016–2020

• B.S. (Hons) in Mathematical Sciences 2016–2020

Publications

• Safe but not Robust: Security Evaluation of VLM by Jailbreaking MSTS — Wenxin Ding, Cong Chen, Jean-Philippe Monteuuis, Jonathan Petit
  • 2026 IEEE Conference on Secure and Trustworthy Machine Learning (SaTML)
• AILuminate Security Introducing v0.5 of the Jailbreak Benchmark from MLCommons (preprint) — James Goel et al
  • [paper]
• Identifying Provenance of Generative Text-to-Image Models — Anna Yoo Jeong Ha, Wenxin Ding*, Stanley Wu*, Shawn Shan, Haitao Zheng, Ben Y. Zhao
  • 2026 USENIX Security
• Understanding Implosion in Text-to-Image Generative Models — Wenxin Ding, Cathy Li, Shawn Shan, Ben Y. Zhao, Haitao Zheng
  • 2024 ACM Conference on Computer and Communications Security (CCS)
  • [paper], [presentation video]
• Towards Scalable and Robust Model Versioning — Wenxin Ding, Arjun Nitin Bhagoji, Ben Y. Zhao, Haitao Zheng
  • 2024 IEEE Conference on Secure and Trustworthy Machine Learning (SaTML)
  • [paper], [presentation video]
• Nightshade: Prompt-Specific Poisoning Attacks on Text-to-Image Generative Models — Shawn Shan, Wenxin Ding, Josephine Passananti, Stanley Wu, Haitao Zheng, Ben Y. Zhao
  • 2024 IEEE Symposium on Security and Privacy (S&P)
  • [paper], [presentation video], [website], [media coverage]
• Characterizing the Optimal 0-1 Loss for Multi-class Classification with a Test-time Attacker — Sihui Dai*, Wenxin Ding*, Arjun Nitin Bhagoji, Daniel Cullina, Ben Y. Zhao, Haitao Zheng, Prateek Mittal
  • 2023 Conference on Neural Information Processing Systems (NeurIPS) (Spotlight)
  • [paper], [presentation video]
• Post-breach Recovery: Protection against White-box Adversarial Examples for Leaked DNN Models — Shawn Shan, Wenxin Ding, Emily Wenger, Haitao Zheng, Ben Y. Zhao
  • 2022 ACM Conference on Computer and Communications Security (CCS)
  • [paper], [website]
• Calibration with Privacy in Peer Review — Wenxin Ding, Gautam Kamath, Weina Wang, Nihar B. Shah
  • 2022 IEEE International Symposium on Information Theory (ISIT)
  • 2022 AAAI Privacy-Preserving Artificial Intelligence (PPAI) Workshop (Spotlight)
  • [paper], [presentation video]
• On the Privacy-Utility Tradeoff in Peer-Review Data Analysis — Wenxin Ding, Nihar B. Shah, Weina Wang
  • 2021 AAAI Privacy-Preserving Artificial Intelligence (PPAI) Workshop (Spotlight)
  • [paper], [presentation video]

Awards

• 2025 University of Chicago William Rainey Harper Dissertation Fellowship
• 2024 University of Chicago UU Fellowship
• 2021 – 2026 University of Chicago Eckhardt Scholar
• 2020 Carnegie Mellon University Senior Leadership Recognition
• 2019 Mark Stehlik SCS Alumni Undergraduate Impact Scholarship
• 2017 William Lowell Putnam Mathematical Competition (Rank: 255 / 4638)

Teaching Assistant

University of Chicago

• CMSC 25800: Adversarial Machine Learning
• CMSC 25300/35300 Mathematical Foundations of Machine Learning

Carnegie Mellon University

• 15110 Principles of Computing (Head TA)
• 15213 Introduction to Computer Systems
• 15440 Distributed Systems