论文标题
关于对抗训练的CNN的性能
On the Properties of Adversarially-Trained CNNs
论文作者
论文摘要
事实证明，对抗性训练是一种有效的训练范式，可以对现代神经网络体系结构中的对抗性实例实施鲁棒性。尽管做出了许多努力，但对对抗训练有效性的基本原则的解释受到限制，并且远未被深度学习社区广泛接受。在本文中，我们描述了对抗训练的模型的令人惊讶的特性，并阐明了对对抗性攻击的鲁棒性进行的机制。此外，我们重点介绍了影响这些模型的局限性和故障模式，这些模型未通过先前的工作讨论。我们对广泛的体系结构和数据集进行了广泛的分析，在健壮模型和自然模型之间进行了深入的比较。
Adversarial Training has proved to be an effective training paradigm to enforce robustness against adversarial examples in modern neural network architectures. Despite many efforts, explanations of the foundational principles underpinning the effectiveness of Adversarial Training are limited and far from being widely accepted by the Deep Learning community. In this paper, we describe surprising properties of adversarially-trained models, shedding light on mechanisms through which robustness against adversarial attacks is implemented. Moreover, we highlight limitations and failure modes affecting these models that were not discussed by prior works. We conduct extensive analyses on a wide range of architectures and datasets, performing a deep comparison between robust and natural models.
