People

I am honored to work with a group of talented students and researchers dedicated to advancing AI safety, AI security and multimodal data protection. Our lab focuses on building trustworthy AI ecosystems through innovative research and collaborative learning.

Current Students

Ph.D. Students (Co-supervised)

Weichen Lian (Fall 2021 - present)

• Research Interests: Deepfake Detection
• Affiliation: Zhejiang University

Bin Gong (Fall 2020 - present)

• Research Interests: IoT Security \& Deepfake Detection
• Affiliation: Zhejiang University

Qing Wen (Fall 2022 - present)

• Research Interests: Deepfake Detection
• Affiliation: Zhejiang University

Yitao Zhang (Fall 2022 - present)

• Research Interests: Watermark Security
• Affiliation: Zhejiang University

Shengwang Xu (Fall 2024 - present)

• Research Interests: AIGC compliance
• Affiliation: Zhejiang University

Master’s Students (Co-supervised)

Ziping Dong (Fall 2023 - present)

• Research Interests: Watermark Security
• Affiliation: Zhejiang University

Zhe Xu (Fall 2023 - present)

• Research Interests: Deepfake Detection
• Affiliation: Zhejiang University

Liang Yi (Fall 2023 - present)

• Research Interests: Speech Toxicity Detection
• Affiliation: Zhejiang University

Zhengheng Han (Fall 2024 - present)

• Research Interests: Deepfake Detection \& Network Security
• Affiliation: Zhejiang University

Miao He (Fall 2024 - present)

• Research Interests: Deepfake Detection
• Affiliation: Zhejiang University

Qingcao Li (Fall 2024 - present)

• Research Interests: Deepfake Detection
• Affiliation: Zhejiang University

Yi Wang (Fall 2025 - present)

• Research Interests: To be updated
• Affiliation: Zhejiang University

Bachelor’s Students (Co-supervised)

Haohao Li (Fall 2025 - present)

• Research Interests: To be updated
• Affiliation: Zhejiang University

Alumni

Ph.D. Students

Xinyu Zhang (Fall 2020 - Spring 2023)

• Research Interests: Speech Understanding & Synthesis
• Current Position: Tongyi Lab, Alibaba Group

Liu Liu (Fall 2020 - Summer 2025)

• Current Position: Zhejiang Police College

Master’s Students

Jiachen Lei (Fall 2020 - Spring 2023)

• Research Interests: Large Generative Models
• Current Position: Alibaba Group (Beijing)

Yuexin Wu (Fall 2020 - Spring 2023)

• Current Position: Ant Group (Hangzhou)

Qiaomu Zheng (Fall 2021 - Summer 2024)

• Current Position: Police Station

Yuwei Wang (Fall 2021 - Spring 2024)

• Current Position: Huawei (Shanghai)

Jieming Zhong (Fall 2022 - Spring 2025)

• Current Position: State Grid (Xiamen)

Undergraduate Students

Qile Zhang (Fall 2024 - Summer 2025)

• Current Position: Master Student at University of California San Diego (UCSD)

Research Areas

Our lab focuses on several interconnected research areas:

• AI-Generated Content Safety \& Security: Privacy preservation, controllability, authenticity, and compliance
• Multimodal Data Privacy: Cross-modal vulnerabilities and privacy-preserving technologies
• IoT Security: Smart device security

Student Achievements

Recent Highlights

• NeurIPS 2025 - Congratulations to Ziping Dong for wmcopier paper acceptance at NeurIPS 2025
• IJCAI 2025 DDL Challenge - Our team achieved 3rd Place in Deepfake Detection and Localization Challenge (2025)
• National Graduate Scholarship (China) - One co-supervised Master’s student (October 2024)
• National Grand Prize - 19th “Challenge Cup” National Competition advisor role (2024)
• Top 5 Nationwide - 3rd China Artificial Intelligence Competition advisor role (2021)

Opportunities

For Prospective Students

We welcome motivated students interested in:

• Ph.D. positions: Full-time research in AI security and privacy
• Master’s positions: Project-based research with publication opportunities
• Undergraduate research: SRTP and summer research programs
• Visiting positions: Short-term and long-term collaboration opportunities

Contact

If you are interested in joining our research group, please contact me with:

• Your CV and research interests
• Relevant coursework and project experience
• Career goals and research vision

“The best way to predict the future is to create it. In our lab, we create the future of AI security through collaborative research, innovative thinking, and dedicated mentorship.”