论文标题
基于梯度的对抗和分布外检测
Gradient-Based Adversarial and Out-of-Distribution Detection
论文作者
论文摘要
我们建议利用梯度检测对抗和分布样本。我们介绍了混杂的标签（与训练过程中的正常标签不同），以探测神经网络的有效表达性。梯度描述了模型正确表示给定输入所需的变化量，从而洞悉了网络体系结构属性建立的模型的代表力以及培训数据。通过引入不同设计的标签，我们消除了推理期间梯度生成的对地面真相标签的依赖。我们表明，我们的基于梯度的方法可以根据模型的有效表达性捕获异常，而没有超级参数调整或其他处理，并且要优于对抗和分布检测的最先进方法。
We propose to utilize gradients for detecting adversarial and out-of-distribution samples. We introduce confounding labels -- labels that differ from normal labels seen during training -- in gradient generation to probe the effective expressivity of neural networks. Gradients depict the amount of change required for a model to properly represent given inputs, providing insight into the representational power of the model established by network architectural properties as well as training data. By introducing a label of different design, we remove the dependency on ground truth labels for gradient generation during inference. We show that our gradient-based approach allows for capturing the anomaly in inputs based on the effective expressivity of the models with no hyperparameter tuning or additional processing, and outperforms state-of-the-art methods for adversarial and out-of-distribution detection.
