Latent Diffusion Shield - Mitigating Malicious Use of Diffusion Models Through Latent Space Adversarial Perturbations
IEEE/CVF Winter Conference on Applications of Computer Vision（2025）
Key words
Diffusion Model,Latent Space,Adversarial Perturbations,Malicious Use,Image Synthesis,Protection Methods,High Computational Demand,Time Step,Computational Cost,Learning Rate,Denoising,Input Image,Diffusion Process,Gaussian Blur,Latent Representation,Variational Autoencoder,Preprocessing Methods,Pixel Spacing,GPU Memory,Adversarial Attacks,Adversarial Examples,Fréchet Inception Distance,JPEG Compression,Numerical Artifacts
AI Read Science
Must-Reading Tree
Example
Generate MRT to find the research sequence of this paper
Chat Paper
Summary is being generated by the instructions you defined