Model Inversion Attacks Through Target-Specific Conditional Diffusion Models
Model inversion attacks (MIAs) aim to reconstruct private images from a target classifier's training set, thereby raising privacy concerns in AI applications. Previous GAN-based MIAs tend to suffer from inferior generative fidelity due to GANs’ inherent flaws and biased optimization within the latent space. To alleviat...
Ouxiang Li, Yanbin Hao, Zhicai Wang et al.
· ACM Transactions on Multimed... · 2 citations