3 papers
cs.CV2025
EIRES:Training-free AI-Generated Image Detection via Edit-Induced Reconstruction Error Shift
Wan Jiang, Jing Yan, Xiaojing Chen +4
Diffusion models have recently achieved remarkable photorealism, making it increasingly difficult to distinguish real images from generated ones, raising significant privacy and se…
cs.LG2024
Moderating the Generalization of Score-based Generative Model
Wan Jiang, He Wang, Xin Zhang +4
Score-based Generative Models (SGMs) have demonstrated remarkable generalization abilities, e.g. generating unseen, but natural data. However, the greater the generalization power,…
cs.LG2023
Unlearnable Examples Give a False Sense of Security: Piercing through Unexploitable Data with Learnable Examples
Wan Jiang, Yunfeng Diao, He Wang +3
Safeguarding data from unauthorized exploitation is vital for privacy and security, especially in recent rampant research in security breach such as adversarial/membership attacks.…