论文标题
了解深神经网络的对抗性鲁棒性的最新进展
Recent Advances in Understanding Adversarial Robustness of Deep Neural Networks
论文作者
论文摘要
在深神经网络（DNN）普遍应用的道路上，对抗性例子是不可避免的。对天然样品应用的不可感知的扰动可以导致基于DNN的分类器以公平的置信度评分输出错误的预测。获得具有较高鲁棒性的模型越来越重要，对对抗性例子有抵抗力。在本文中，我们调查了如何从不同的角度理解这种有趣的财产，即对对抗性的鲁棒性的最新进展。我们给出有关哪些对抗性攻击和鲁棒性的初步定义。之后，我们研究了经常使用的基准测试，并提及理论上具有对抗性鲁棒性的界限。然后，我们提供了分析对抗性鲁棒性和DNN模型其他关键指标之间相关性的概述。最后，我们介绍了有关对抗训练的潜在成本的最新论点，这些论点引起了研究界的广泛关注。
Adversarial examples are inevitable on the road of pervasive applications of deep neural networks (DNN). Imperceptible perturbations applied on natural samples can lead DNN-based classifiers to output wrong prediction with fair confidence score. It is increasingly important to obtain models with high robustness that are resistant to adversarial examples. In this paper, we survey recent advances in how to understand such intriguing property, i.e. adversarial robustness, from different perspectives. We give preliminary definitions on what adversarial attacks and robustness are. After that, we study frequently-used benchmarks and mention theoretically-proved bounds for adversarial robustness. We then provide an overview on analyzing correlations among adversarial robustness and other critical indicators of DNN models. Lastly, we introduce recent arguments on potential costs of adversarial training which have attracted wide attention from the research community.
