I am Yi Zhang (张艺), a third-year Ph.D. student at the Warwick Manufacturing Group (WMG), University of Warwick. I am fortunate to be supervised by Prof. Xingyu Zhao and Prof. Siddartha Khastgir. Before beginning my Ph.D. journey, I received both my Bachelor's and Master's degrees in Computer Science from Beijing Language and Culture University (BLCU). My Master's research focused on Natural Language Processing (NLP), particularly on knowledge graphs and semantic understanding, under the supervision of Prof. Endong Xun.

My current research interests include:

• Probabilistic Robustness
• Safe and Reliable Generative Models
• Vision-Language Foundation Models
• Trustworthy Artificial Intelligence (AI)

🔥 News

• 2026.07: 🏆🏆 I received the Best Paper Award and gave an oral presentation, “Probabilistic Robustness in Medical Image Classification”, at the Faculty of Science, Engineering and Medicine Early Career Researcher Symposium 2026, University of Warwick.
• 2026.05: 🎉🎉 Our paper, PRBench: A Standardized Probabilistic Robustness Benchmark , has been accepted by KDD 2026.
• 2026.05: 🎉🎉 Our paper, Non-Parametric Probabilistic Robustness: A Conservative Risk Estimator under Unknown Perturbation Distributions , has been accepted by ICML 2026.
• 2026.02: 🎉🎉 Our paper, Trustworthy text-to-image diffusion models: A timely and focused survey , has been accepted by Information Fusion.
• 2025.11: 🎉🎉 Our paper, Fragile by Design: On the Limits of Adversarial Defenses in Personalized Generation , has been accepted by AAAI 2026.
• 2025.07: 🎉🎉 Our paper, Adversarial Training for Probabilistic Robustness , has been accepted by ICCV 2025.
• 2025.07: 🏆🏆 I received the Warwick Star Award! Postgraduate Research Student Award — Excellence in Innovation.
• 2024.12: 🚀🚀 I was supported by the NVIDIA Academic Grant Program .
• 2024.09: 🎉🎉 Our paper, TARP-VP: Towards Evaluation of Transferred Adversarial Robustness and Privacy on Label Mapping Visual Prompting Models , has been accepted by NeurIPS 2024.
• 2024.06: 🎉🎉 Our paper, ProTIP: Probabilistic Robustness Verification on Text-to-Image Diffusion Models against Stochastic Perturbation , has been accepted by ECCV 2024.
• 2024.03: 🎉🎉 Our paper, Augmenting Scenario Description Languages for Intelligence Testing of Automated Driving Systems , has been accepted by IV 2024.
• 2023.12: 🎉🎉 Our paper, Long-term memory for large language models through topic-based vector database , has been accepted by IALP 2023.

📝 Publications

• PRBench: A Standardized Probabilistic Robustness Benchmark  
  Yi Zhang, Zheng Wang, Zhen Chen, Wenjie Ruan, Qing Guo, Siddartha Khastgir, carsten maple, Xingyu Zhao
  [KDD 2026]   [Paper]   [GitHub]   [Leaderboard]
• Non-Parametric Probabilistic Robustness: A Conservative Risk Estimator under Unknown Perturbation Distributions
  Zheng Wang, Yi Zhang, Siddartha Khastgir, Carsten Maple, Xingyu Zhao
  [ICML 2026]   [Paper]  
• Trustworthy text-to-image diffusion models: A timely and focused survey
  Yi Zhang, Zhen Chen, Chih-Hong Cheng, Wenjie Ruan, Xiaowei Huang, Dezong Zhao, David Flynn, Siddartha Khastgir, Xingyu Zhao
  [Information Fusion]   [Paper]   [GitHub]  
• Fragile by Design: On the Limits of Adversarial Defenses in Personalized Generation
  Zhen Chen, Yi Zhang, Xiangyu Yin, Chengxuan Qin, Xingyu Zhao, Xiaowei Huang, Wenjie Ruan
  [AAAI 2026]   [Paper]  
• Adversarial Training for Probabilistic Robustness
  Yi Zhang, Yuhang Chen, Zhen Chen, Wenjie Ruan, Xiaowei Huang, Siddartha Khastgir, Xingyu Zhao
  [ICCV 2025]   [Paper]   [GitHub]  
• ProTIP: Probabilistic Robustness Verification on Text-to-Image Diffusion Models against Stochastic Perturbation
  Yi Zhang, Yun Tang, Wenjie Ruan, Xiaowei Huang, Siddartha Khastgir, Paul Jennings, Xingyu Zhao
  [ECCV 2024]   [Paper]   [GitHub]  
• Augmenting Scenario Description Languages for Intelligence Testing of Automated Driving Systems
  Yun Tang, Antonio A Bruto Da Costa, Patrick Irvine, Tudor Dodoiu, Yi Zhang, Xingyu Zhao, Siddartha Khastgir, Paul Jennings
  [IV 2024]   [Paper]  
• TARP-VP: Towards Evaluation of Transferred Adversarial Robustness and Privacy on Label Mapping Visual Prompting Models
  Zhen Chen, Yi Zhang, Fu Wang, Xingyu Zhao, Xiaowei Huang, Wenjie Ruan
  [NeurIPS 2024]   [Paper]  
• Long-term memory for large language models through topic-based vector database
  Yi Zhang, Zhongyang Yu, Wanqi Jiang, Yufeng Shen, Jin Li
  [IALP 2023]   [Paper]  
• Distant Supervision For Chinese Semantic Role Labeling
  Yi Zhang, Guirong Wang, Endong Xun
  [IALP 2022]   [Paper]  
• Chinese Argument Identification Based on Bert
  Yi Zhang, Guirong Wang, Ye Xiao, Endong Xun
  [CLSW 2022]   [Paper]  

👩‍💻 Experience

• OpenDOC
  NLP Algorithm Lead Engineer (Dec 2022 – Sep 2023)


• ByteDance AI-Lab
  NLP Algorithm Project Engineer Intern (Apr 2022 – Aug 2022)


• DiDi Global Inc.
  NLP Algorithm Project Engineer Intern (Sep 2021 – Mar 2022)

💬 Invited Talks

• 2026.04: Journal of Reliability Science and Engineering: Probabilistic Robustness and Trustworthy Verification of AI/ML Models.

👩‍🏫 Academic Services

• Reviewer: ICLR, ICCV, ECCV, CVPR...

🎓 Education Background

• The University of Warwick
  Ph.D. in Engineering, Oct 2023 – Oct 2027


• Beijing Language and Culture University
  M.Sc. in Computer Science, Sep 2020 – Jul 2023


• Beijing Language and Culture University
  B.Eng. in Computer Science, Sep 2016 – Jul 2020