Xiao-Shan Gao

Analyzing stability in adversarial training to enhance model generalization.

Understanding unlearnable example attacks through game theory for better data protection.

New methods to safeguard sensitive data against unauthorized access in machine learning.

Introducing new methods to improve forgetting processes in contrastive learning models.

Introducing FC-EM to protect 3D point cloud data from unauthorized access.

Examining vulnerabilities from clean-label backdoor attacks and how generalization bounds can help.

PowerMLP offers a speedy solution for efficient neural network training.

Learn about data protection methods and threats in the machine learning landscape.