CV

Education

• Ph.D in EIC School, Huazhong University of Science and Technology (HUST), 2025-2029 (expected)
• M.S. in EIC School, Huazhong University of Science and Technology (HUST), 2022-2025
• B.S. in PST School, Central China Normal University (CCNU), 2018-2022

Skills

• Systems (Linux or Ubuntu)
• Python (Pytorch, Torchvision, ultralytics, Transformers, …)
• Office
  • Visio
  • Word
  • Powerpoint
• Latex/Overleaf
• Origin

Publications

Black-Box Membership Inference Attacks against Contrastive Learning via Aggressive Data Augmentations

Fingerprinting Pre-trained Encoders under Arbitary Downstream Fine-tuning via Adversarial Shifting

Breaking the Boundary Barrier: Robust Model Fingerprinting via Unlearnable Examples in Model-Parameter Space

Decoupling Memories, Muting Neurons: Towards Practical Machine Unlearning for Large Language Models

Prototype Surgery: Tailoring Neural Prototypes via Soft Labels for Efficient Machine Unlearning

Gradient-Leaks: Enabling Black-Box Membership Inference Attacks Against Machine Learning Models

Knowledge Representation of Training Data With Adversarial Examples Supporting Decision Boundary

Competition Experience

• The Challenge Cup 2025 games (Team Leader). Grand Prize in the SH-04 track @Shanghai.