Adversarial Examples on Object Recognition: A Comprehensive Survey
This is an incremental survey paper that addresses security, safety, and robustness issues in neural networks for researchers and practitioners.
The paper surveys the problem of adversarial examples in deep neural networks, where small input perturbations cause incorrect behavior, and reviews hypotheses, construction methods, and defenses to provide a comprehensive overview of the field.
Deep neural networks are at the forefront of machine learning research. However, despite achieving impressive performance on complex tasks, they can be very sensitive: Small perturbations of inputs can be sufficient to induce incorrect behavior. Such perturbations, called adversarial examples, are intentionally designed to test the network's sensitivity to distribution drifts. Given their surprisingly small size, a wide body of literature conjectures on their existence and how this phenomenon can be mitigated. In this article we discuss the impact of adversarial examples on security, safety, and robustness of neural networks. We start by introducing the hypotheses behind their existence, the methods used to construct or protect against them, and the capacity to transfer adversarial examples between different machine learning models. Altogether, the goal is to provide a comprehensive and self-contained survey of this growing field of research.