Generalizable Adversarial Attacks Using Generative Models
share
Adversarial attacks on deep neural networks traditionally rely on a constrained optimization paradigm, where an optimization procedure is used to obtain a single adversarial perturbation for a given input example. Here, we instead view adversarial attacks as a generative modelling problem, with the goal of producing entire distributions of adversarial examples given an unperturbed input. We show that this generative perspective can be used to design a unified encoder-decoder framework, which is domain-agnostic in that the same framework can be employed to attack different domains with minimal modification. Across three diverse domains---images, text, and graphs---our approach generates whitebox attacks with success rates that are competitive with or superior to existing approaches, with a new state-of-the-art achieved in the graph domain. Finally, we demonstrate that our generative framework can efficiently generate a diverse set of attacks for a single given input, and is even capable of attacking unseen test instances in a zero-shot manner, exhibiting attack generalization.
READ FULL TEXT