Zhengyu Zhao

Full Professor, Xi'an Jiaotong University

Joined

November 2019

Names

Zhengyu Zhao (Preferred)

Emails

****@cs.ru.nl (Confirmed)

****@cispa.de (Confirmed)

****@gmail.com (Confirmed)

****@xjtu.edu.cn (Confirmed)

Personal Links

Career & Education History

Full Professor

Xi'an Jiaotong University (xjtu.edu.cn)

2024 – Present

Associate Professor

Xi'an Jiaotong University (xjtu.edu.cn)

2023 – 2024

Postdoc

CISPA Helmholtz Center for Information Security (cispa.de)

2021 – 2023

PhD student

Radboud University (ru.nl)

2017 – 2021

Advisors, Relations & Conflicts

Postdoc Advisor

Michael Backes

2021 – 2023

PhD Advisor

Martha Larson

2017 – 2021

Expertise

Adversarial Machine Learning

2019 – Present

Computer Vision

2017 – Present

Publications

Revisiting Transferable Adversarial Images: Systemization, Evaluation, and New Insights
Zhengyu Zhao, Hanwei Zhang, Renjue Li, Ronan Sicre, laurent amsaleg, Michael Backes
- OpenReview Archive Direct Upload
- Readers: Everyone
Prediction Inconsistency Helps Generalizable Detection of Adversarial Examples
Sicong Han, Chenhao Lin, Zhengyu Zhao, Xiyuan Wang, Xinlei He, Qian Li, Cong Wang, Qian Wang, Chao Shen
- ICLR 2026 Conference Withdrawn Submission
- Readers: Everyone
Enhancing Query-Free Jailbreaks on Text-to-Image Models with Bimodal Guidance
Yuchen Ren, Yufei Chen, Bo Yang, Chenhao Lin, Cong Wang, Chao Shen, Zhengyu Zhao
- ICLR 2026 Conference Withdrawn Submission
- Readers: Everyone
AdvFLYP: Adversarially Finetune Like You Pretrain for Zero-shot Robustness of CLIP
Songlong Xing, Weijie Wang, Zhengyu Zhao, Nicu Sebe
- ICLR 2026 Conference Withdrawn Submission
- Readers: Everyone
Seeing It or Not? Interpretable Vision-aware Latent Steering to Mitigate Object Hallucinations
Boxu Chen, Ziwei Zheng, Le Yang, Zeyu Geng, Zhengyu Zhao, Chenhao Lin, Chao Shen
- ICLR 2026 Conference Withdrawn Submission
- Readers: Everyone
Pay Less Attention to Function Words for Free Robustness of Vision-Language Models
Qiwei Tian, Chenhao Lin, Zhengyu Zhao, Chao Shen
- ICLR 2026 Poster
- Readers: Everyone
Improving Integrated Gradient-based Transferable Adversarial Examples by Refining the Integration Path
Yuchen Ren, Zhengyu Zhao, Chenhao Lin, Bo Yang, Lu Zhou, Zhe Liu, Chao Shen
- AAAI 2025
- Readers: Everyone
Adversarial Example Soups: Improving Transferability and Stealthiness for Free
Bo Yang, Hengwei Zhang, Jindong Wang, Yulong Yang, Chenhao Lin, Chao Shen, Zhengyu Zhao
- IEEE Transactions on Information Forensics and Security
- Readers: Everyone
Hard Adversarial Example Mining for Improving Robust Fairness
Chenhao Lin, Xiang Ji, Yulong Yang, Qian Li, Zhengyu Zhao, Zhe Peng, Run Wang, Liming Fang, Chao Shen
- IEEE Trans. Inf. Forensics Secur. 2025
- Readers: Everyone
Breaking Semantic Artifacts for Generalized AI-generated Image Detection
Chende Zheng, Chenhao Lin, Zhengyu Zhao, Hang Wang, Xu Guo, Shuai Liu, Chao Shen
- NeurIPS 2024 poster
- Readers: Everyone

View all 37 publications

Co-Authors

View all 58 co-authors