Convolutional neural networks (CNN) define the state-of-the-art solution on many perceptual tasks. However, current CNN approaches largely remain vulnerable against adversarial perturbations of the input that have been crafted specifically to fool the system while being quasi-imperceptible to the human eye. In recent years, various approaches have been proposed to defend CNNs against such attacks, for example by model hardening or by adding explicit defence mechanisms. Thereby, a small "detector" is included in the network and trained on the binary classification task of distinguishing genuine data from data containing adversarial perturbations. In this work, we propose a simple and light-weight detector, which leverages recent findings on the relation between networks' local intrinsic dimensionality (LID) and adversarial attacks. Based on a re-interpretation of the LID measure and several simple adaptations, we surpass the state-of-the-art on adversarial detection by a significant margin and reach almost perfect results in terms of F1-score for several networks and datasets. Sources available at: https://github.com/adverML/multiLID

翻译：卷积神经网络（CNN）定义了多项感知任务中的最优解决方案。然而，当前的CNN方法在应对针对系统精心设计、对人类视觉几乎不可察觉的对抗性输入扰动时仍存在显著脆弱性。近年来，研究者提出了多种方法来防御此类攻击，例如通过模型硬化或添加显式防御机制。其中一种方法是向网络中集成一个轻量级“检测器”，并训练其完成区分真实数据与含有对抗扰动的数据的二分类任务。本文提出了一种简单且轻量的检测器，该检测器利用了近期关于网络局部内在维度（LID）与对抗攻击之间关系的研究发现。通过对LID度量的重新诠释及若干简单改进，我们在对抗检测任务上以显著优势超越了当前最优方法，并在多个网络和数据集上达到了近乎完美的F1分数。源代码见：https://github.com/adverML/multiLID