-
University of Science and Technology Beijing
- Beijing
Stars
code of paper "IMPRESS: Evaluating the Resilience of Imperceptible Perturbations Against Unauthorized Data Usage in Diffusion-Based Generative AI"
Official repo to reproduce the paper "How to Backdoor Diffusion Models?" published at CVPR 2023
ACM MM 2023 | Learning a Graph Neural Network with Cross Modality Interaction for Image Fusion
(AAAI 2024) Transferable Adversarial Attacks for Object Detection using Object-Aware Significant Feature Distortion
(AAAI 24) Step Vulnerability Guided Mean Fluctuation Adversarial Attack against Conditional Diffusion Models