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 over a test window and fires off an alarm whenever a deviation is detected. This novel detection method consistently and significantly outperforms the state of the art with respect to the CIFAR-10 and ImageNet datasets, thus establishing a new performance bar for this task, while being substantially more efficient in time and space complexities.

翻译：为在产环境中部署和运行深度神经模型，必须监控和评估其预测质量——这些质量可能因输入分布偏差的良性污染或恶意操纵而受损。具体而言，我们研究监控接收数据流的深度神经网络(DNN)健康运行的情况，旨在检测可能导致网络预测质量受损的输入分布偏差。利用选择性预测原理，我们提出了一种适用于DNN的分布偏差检测方法。该方法基于从真实底层分布中抽取样本实例的紧致覆盖泛化界推导而来。依据该界限，我们的检测器持续监控网络在测试窗口上的运行状态，一旦检测到偏差便触发警报。这一新颖的检测方法在CIFAR-10和ImageNet数据集上始终显著优于现有技术水平，为该任务树立了新的性能标杆，同时在时间和空间复杂度上更为高效。