Picture for Chengjun Cai

Chengjun Cai

GReDP: A More Robust Approach for Differential Privacy Training with Gradient-Preserving Noise Reduction

Add code
Sep 18, 2024
Viaarxiv icon

Arondight: Red Teaming Large Vision Language Models with Auto-generated Multi-modal Jailbreak Prompts

Add code
Jul 21, 2024
Viaarxiv icon