Greedy Attack and Gumbel Attack: Generating Adversarial Examples for Discrete Data

Authors: Puyudi Yang, Jianbo Chen, Cho-Jui Hsieh, Jane-Ling Wang, Michael I. Jordan
Published: 2018-05-31

Source: https://arxiv.org/abs/1805.12316

PDF: https://arxiv.org/pdf/1805.12316

Labels Predicted by AI

敵対的移転性 特徴重要度分析 透かし評価

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

We present a probabilistic framework for studying adversarial attacks on discrete data. Based on this framework, we derive a perturbation-based method, Greedy Attack, and a scalable learning-based method, Gumbel Attack, that illustrate various tradeoffs in the design of attacks. We demonstrate the effectiveness of these methods using both quantitative metrics and human evaluation on various state-of-the-art models for text classification, including a word-based CNN, a character-based CNN and an LSTM. As as example of our results, we show that the accuracy of character-based convolutional networks drops to the level of random selection by modifying only five characters through Greedy Attack.