Adversarial Jamming for Autoencoder Distribution Matching

TL;DR

This paper introduces a novel adversarial jamming technique to regularize autoencoder latent spaces, effectively matching them to a Gaussian distribution and improving distribution matching performance.

Contribution

The paper presents a new adversarial jamming method for latent space regularization, inspired by theoretical minimax game results, enhancing distribution matching in autoencoders.

Findings

Achieves distribution matching comparable to variational and Wasserstein autoencoders.

Utilizes adversarial jamming as an auxiliary objective for latent space regularization.

Method can be generalized to other latent distributions.

Abstract

We propose the use of adversarial wireless jamming to regularise the latent space of an autoencoder to match a diagonal Gaussian distribution. We consider the minimisation of a mean squared error distortion, where a jammer attempts to disrupt the recovery of a Gaussian source encoded and transmitted over the adversarial channel. A straightforward consequence of existing theoretical results is the fact that the saddle point of a minimax game - involving such an encoder, its corresponding decoder, and an adversarial jammer - consists of diagonal Gaussian noise output by the jammer. We use this result as inspiration for a novel approach to distribution matching in the latent space, utilising jamming as an auxiliary objective to encourage the aggregated latent posterior to match a diagonal Gaussian distribution. Using this new technique, we achieve distribution matching comparable to standard variational autoencoders and to Wasserstein autoencoders. This approach can also be generalised to other latent distributions.