Defending Adversaries Using Unsupervised Feature Clustering VAE
We propose a modified VAE (variational autoencoder) as a denoiser to remove adversarial perturbations for image classification. Vanilla VAE's purpose is to make latent variables approximating normal distribution, which reduces the latent inter-class distance of data points. Our proposed VAE modifies this problem by adding a latent variable cluster. So the VAE can guarantee inter-class distance of latent variables and learn class-wised features. Our Feature Clustering VAE performs better on removing perturbations and reconstructing the image to defend adversarial attacks.
PDF Abstract
Datasets
Add Datasets
introduced or used in this paper
Results from the Paper
Submit
results from this paper
to get state-of-the-art GitHub badges and help the
community compare results to other papers.
