I am currently a Second Year Ph.D. Candidate at Zhejiang University, advised by Prof. Shouling Ji. I received my B.S. degree with honors in Computer Science from Ningbo University (Yangming Class), advised by Prof. Diqun Yan. My research focuses on Trustworthy Generative AI in real-world applications, especially AI Security, AI Copyright Protection, and Privacy-Preserving AI. My long-term goal is to strengthen the source governance of AI technology and rectify illegal AI applications. Recently, I have been focusing more on the Security and Privacy risks of MLLMs and T2I models.
🔥 News
- 2025.07: 🎉🎉 One paper was accepted by MM 2025.
- 2025.05: 🎉🎉 One paper was accepted by ACL 2025.
- 2025.04: 🎉🎉 One paper was accepted by TDSC 2025.
- 2025.04: 🎉🎉 One paper was accepted by ICMR 2025 Oral.
- 2025.03: 🎉🎉 One paper was accepted by ICME 2025 Oral.
- 2024.10: 🎉🎉 Two papers were accepted by AAAI 2025.
📝 Publications
- Enhancing Adversarial Transferability with Adversarial Weight Tuning, Jiahao Chen*, Zhou Feng*, Rui Zeng, Yuwen Pu, Chunyi Zhou, Yi Jiang, Yuyou Gan, Jinbao Li, Shouling Ji, AAAI 2025. [CCF-A] [Code]
- CAMH: Advancing Model Hijacking Attack in Machine Learning, Xing He*, Jiahao Chen*, Yuwen Pu, Qingming Li, Chunyi Zhou, Yingcai Wu, Jinbao Li, Shouling Ji, AAAI 2025. [CCF-A] [Code]
- Facial data minimization: Shallow model as your privacy filter, Yuwen Pu*, Jiahao Chen*, Jiayu Pan, Diqun Yan, Xuhong Zhang, Shouling Ji, TDSC 2025. [CCF-A]
- Enkidu: Universal Frequential Perturbation for Real-Time Audio Privacy Protection against Voice Deepfakes, Zhou Feng, Jiahao Chen, Chunyi Zhou, Yuwen Pu, Qingming Li, Tianyu Du, Shouling Ji, MM 2025. [CCF-A]
- TWIST: Text-encoder Weight-editing for Inserting Secret Trojans in Text-to-Image Models, Xindi Li, Zhe Liu, Tong Zhang, Jiahao Chen, Qingming Li, Jinbao Li, Shouling Ji, ACL 2025 Main. [CCF-A]
- Universal defensive underpainting patch: Making your text invisible to optical character recognition, JiaCheng Deng, Li Dong, Jiahao Chen, Diqun Yan, Rangding Wang, Dengpan Ye, Lingchen Zhao, Jinyu Tian, ACM MM 2023. [CCF-A] [Code]
- Poison in the Well: Feature Embedding Disruption in Backdoor Attacks, Zhou Feng, Jiahao Chen, Chunyi Zhou, Yuwen Pu, Qingming Li, Shouling Ji, ICME 2025 Oral. [CCF-B]
- Enhancing Adversarial Transferability via Self-Ensemble Feature Alignment, Zhiming Zhao, Jiahao Chen, Qingming Li, Chunyi Zhou, Shouling Ji, ICMR 2025 Oral. [CCF-B]
- AdvUSL: Targeted Adversarial Attack against U-shaped Split Learning, Yunxiao He, Chunqiang Hu, Yuwen Pu, Jiahao Chen, Xingwang Li, MASS 2024. [CCF-C]
📖 Educations
- 2023.09 - now, Ph.D. Candidate, Electronic Information, College of Computer Science and Technology, Zhejiang University.
- 2019.09 - 2023.06, B.E., Computer Science, YangMing College, Ningbo University.
💬 Service
- Reviewers: IEEE TDSC, IEEE TIFS, AAAI, ACM MM