论文标题
Gran：一种有效的基于梯度 - 基于对抗和错误分类示例的检测器
GraN: An Efficient Gradient-Norm Based Detector for Adversarial and Misclassified Examples
论文作者
论文摘要
深度神经网络（DNN）容易受到对抗性示例和其他数据扰动的影响。尤其是在DNN的安全关键应用中，因此检测错误分类的样本至关重要。与原始网络本身相比，当前的最新检测方法需要更多的运行时或更多参数。因此，本文提出了Gran，这是一种易于适应任何DNN的时间和参数效率方法。 Gran基于DNN梯度的层范围，该梯度涉及当前输入输出组合的损失，该组合可以通过反向传播计算。 Gran在众多问题设置上实现了最先进的表现。
Deep neural networks (DNNs) are vulnerable to adversarial examples and other data perturbations. Especially in safety critical applications of DNNs, it is therefore crucial to detect misclassified samples. The current state-of-the-art detection methods require either significantly more runtime or more parameters than the original network itself. This paper therefore proposes GraN, a time- and parameter-efficient method that is easily adaptable to any DNN. GraN is based on the layer-wise norm of the DNN's gradient regarding the loss of the current input-output combination, which can be computed via backpropagation. GraN achieves state-of-the-art performance on numerous problem set-ups.
