Greedy Attack and Gumbel Attack: Generating Adversarial Examples for Discrete Data
Journal of Machine Learning Research, 2020.
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 bo...More
Full Text (Upload PDF)
PPT (Upload PPT)