Search Results for author:
Found 2 papers, 1 papers with code
Membership Inference Attacks against Diffusion Models
We primarily discuss the diffusion model from the standpoints of comparison with a generative adversarial network (GAN) as conventional models and hyperparameters unique to the diffusion model, i. e., time steps, sampling steps, and sampling variances.
MEGEX: Data-Free Model Extraction Attack against Gradient-Based Explainable AI
In this method, an adversary uses the explanations to train the generative model and reduces the number of queries to steal the model.
Cannot find the paper you are looking for? You can
Submit a new open access paper.
