I am a Ph.D student in the Institute of Artificial Intelligence, Beihang University (BUAA), China, and my PhD supervisor is Xingxing Wei. Before that, I received B.S. degree in the School of Computer Science and Engineering, Beihang University (BUAA), China.
My research interest includes, LLMs and MLLMs safety, knowledge distillation, adversarial attack, adversarial robustness in machine learning.
Please feel free to contact me if you are interested in any collaboration. My e-mail: zhaoshiji123@buaa.edu.cn.
π» Experience
- 2022.09 - present, Ph.D Student, the Institute of Artificial Intelligence, Beihang University (BUAA).
- 2021.09 - 2022.07, M.S. Student, the School of Computer Science and Engineering, Beihang University (BUAA).
- 2017.09 - 2021.07, B.S. Student, the School of Computer Science and Engineering, Beihang University (BUAA).
π₯ News
- 2026.03: Β ππ a paper on infrared adversarial robustness is accepted to IJCV 2026.
- 2026.02: Β ππ two papers are accepted to CVPR 2026.
- 2025.09: I will serve as a reviewer for ICML 2026 and ECCV 2026.
- 2025.09: I will serve as a reviewer for ICLR 2026 and CVPR 2026.
- 2025.06: Β ππ two papers on MLLMs safety are accepted to ICCV 2025.
- 2025.04: I will serve as a reviewer for NeurIPS 2025.
- 2025.02: I will serve as a reviewer for ICCV 2025.
- 2025.01: Β ππ I have been selected for Young Talent Support Project Doctoral Program of the China Association for Science and Technology.
- 2024.12: Β ππ I have been awarded the highest honor for students (the Shen Yuan Medal) at Beihang University.
- 2024.12: I will serve as a reviewer for TNNLS.
- 2024.11: I will serve as a reviewer for CVPR 2025.
- 2024.09: Β ππ I have been awarded the National Scholarship.
- 2024.09: Β ππ a paper on Adversarial Robustness are accepted to NeurIPS 2024.
- 2024.06: Β ππ Two papers on Adversarial Robustness are accepted to TPAMI 2024.
- 2023.11: I will serve as a reviewer for CVPR 2024.
π Publications
Knowledge-Guided Adversarial Training for Infrared Object Detection via Thermal Radiation Modeling
Shiji Zhao*, Shukun Xiong*, Maoxun Yuan, Yao Huang, Ranjie Duan, Qing Guo, Jiansheng Chen, Haibin Duan, Xingxing Wei (Supervisor).
International Journal of Computer Vision (IJCV), 2026
VRSA: Jailbreaking Multimodal Large Language Models through Visual Reasoning Sequential Attack
Shiji Zhao*, Shukun Xiong*, Yao Huang, JIN YAN, Zhenyu Wu, Jiyang Guan, Ranjie Duan, Jialing Tao, Hui Xue, Xingxing Wei (Supervisor).
IEEE Conference on Computer Vision and Pattern Recognitionβ (CVPR2026 Findings), 2026
Jailbreaking Multimodal Large Language Models via Shuffle Inconsistency
Shiji Zhao, Ranjie Duan, Fengxiang Wang, Chi Chen, Caixin Kang, Shouwei Ruan, Jialing Tao, YueFeng Chen, Hui Xue, Xingxing Wei (Supervisor).
International Conference on Computer Vision (ICCV), 2025
Improving Adversarial Robust Fairness via Anti-Bias Soft Label Distillation
Shiji Zhao, Xizhe Wang, Ranjie Duan and Xingxing Wei (Supervisor).
The Thirty-eighth Annual Conference on Neural Information Processing Systems (NeurIPS), 2024
Mitigating Accuracy-Robustness Trade-Off Via Balanced Multi-Teacher Adversarial Distillation
Shiji Zhao, Xizhe Wang, and Xingxing Wei (Supervisor).
IEEE Transaction on Pattern Analysis and Machine Intelligence (TPAMI), 2024
Revisiting the Trade-Off Between Accuracy and Robustness Via Weight Distribution of Filters
Xingxing Wei (Supervisor), Shiji Zhao, and Bo Li.
IEEE Transaction on Pattern Analysis and Machine Intelligence (TPAMI), 2024
Boosting adversarial transferability with learnable patch-wise masks
Xingxing Wei (Supervisor), and Shiji Zhao.
IEEE Transactions on Multimedia (TMM), 2023
Enhanced accuracy and robustness via multi-teacher adversarial distillation
Shiji Zhao, Jie Yu, zhenlong Sun, Bo Zhang, Xingxing Wei (Supervisor).
European Conference on Computer Vision (ECCV), 2022