2000 character limit reached
Diagnosing Vulnerability of Variational Auto-Encoders to Adversarial Attacks (2103.06701v3)
Published 10 Mar 2021 in cs.CR, cs.LG, and stat.ML
Abstract: In this work, we explore adversarial attacks on the Variational Autoencoders (VAE). We show how to modify data point to obtain a prescribed latent code (supervised attack) or just get a drastically different code (unsupervised attack). We examine the influence of model modifications ($\beta$-VAE, NVAE) on the robustness of VAEs and suggest metrics to quantify it.
Sponsor
Paper Prompts
Sign up for free to create and run prompts on this paper using GPT-5.
Top Community Prompts
Collections
Sign up for free to add this paper to one or more collections.