论文标题
对象识别的对抗性示例：一项全面调查
Adversarial Examples on Object Recognition: A Comprehensive Survey
论文作者
论文摘要
深度神经网络处于机器学习研究的最前沿。但是，尽管在复杂的任务上取得了令人印象深刻的表现，但它们可能非常敏感：输入的小扰动可能足以引起不正确的行为。这样的扰动（称为对抗性示例）是故意设计的，旨在测试网络对分布漂移的敏感性。鉴于它们的大小出奇的规模，关于其存在的广泛文献以及如何缓解这种现象。在本文中，我们讨论了对抗性示例对神经网络安全性，安全性和鲁棒性的影响。首先，我们引入其存在背后的假设，用于构建或保护它们的方法以及在不同机器学习模型之间传递对抗性示例的能力。总的来说，目标是对这一不断增长的研究领域进行全面且独立的调查。
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.
