To deploy and operate deep neural models in production, the quality of their predictions, which might be contaminated benignly or manipulated maliciously by input distributional deviations, must be monitored and assessed. Specifically, we study the case of monitoring the healthy operation of a deep neural network (DNN) receiving a stream of data, with the aim of detecting input distributional deviations over which the quality of the network's predictions is potentially damaged. Using selective prediction principles, we propose a distribution deviation detection method for DNNs. The proposed method is derived from a tight coverage generalization bound computed over a sample of instances drawn from the true underlying distribution. Based on this bound, our detector continuously monitors the operation of the network out-of-sample over a test window and fires off an alarm whenever a deviation is detected. Our novel detection method performs on-par or better than the state-of-the-art, while consuming substantially lower computation time (five orders of magnitude reduction) and space complexities. Unlike previous methods, which require at least linear dependence on the size of the source distribution for each detection, rendering them inapplicable to ``Google-Scale'' datasets, our approach eliminates this dependence, making it suitable for real-world applications.

翻译：为在生产环境中部署与运行深度神经网络模型，必须对其预测质量进行监控与评估，这些预测可能因输入分布的正常偏差或恶意操纵而受损。具体而言，我们研究如何监控接收数据流的深度神经网络（DNN）的健康运行状态，以检测可能导致网络预测质量下降的输入分布偏差。基于选择性预测原理，我们提出一种针对DNN的分布偏差检测方法。该方法源自对真实底层分布中抽取的样本实例计算得到的紧致覆盖泛化界。基于该泛化界，我们的检测器通过测试窗口持续监控网络在样本外的运行状态，一旦检测到偏差即触发警报。该创新检测方法的性能与现有最优方法相当或更优，同时计算时间（降低五个数量级）和空间复杂度显著降低。与现有方法（每次检测至少需要与源分布规模呈线性依赖关系，因而无法适用于“谷歌规模”数据集）不同，本方法消除了这种依赖关系，使其适用于实际应用场景。