Diagnosing Vulnerability of Variational Auto-Encoders to Adversarial Attacks

Authors: Anna Kuzina, Max Welling, Jakub M. Tomczak
Published: 2021-03-10 | Updated: 2021-05-06

Source: https://arxiv.org/abs/2103.06701

PDF: https://arxiv.org/pdf/2103.06701

Labels Predicted by AI

敵対的攻撃 モデル性能評価 脆弱性分析

Please note that these labels were automatically added by AI. Therefore, they may not be entirely accurate.
For more details, please see the About the Literature Database page.

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 (β-VAE, NVAE) on the robustness of VAEs and suggest metrics to quantify it.