Distribution Shift Detection for Deep Neural Networks

10/19/2022
by   Guy Bar-Shalom, et al.
0

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.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
05/23/2017

Selective Classification for Deep Neural Networks

Selective classification techniques (also known as reject option) have n...
research
06/19/2022

Out-of-distribution Detection by Cross-class Vicinity Distribution of In-distribution Data

Deep neural networks only learn to map in-distribution inputs to their c...
research
07/15/2022

On the Usefulness of Deep Ensemble Diversity for Out-of-Distribution Detection

The ability to detect Out-of-Distribution (OOD) data is important in saf...
research
02/25/2021

Statistical Testing for Efficient Out of Distribution Detection in Deep Neural Networks

Commonly, Deep Neural Networks (DNNs) generalize well on samples drawn f...
research
07/31/2020

Practical Detection of Trojan Neural Networks: Data-Limited and Data-Free Cases

When the training data are maliciously tampered, the predictions of the ...
research
02/22/2022

Model2Detector: Widening the Information Bottleneck for Out-of-Distribution Detection using a Handful of Gradient Steps

Out-of-distribution detection is an important capability that has long e...
research
11/16/2020

Online Monitoring of Object Detection Performance Post-Deployment

Post-deployment, an object detector is expected to operate at a similar ...

Please sign up or login with your details

Forgot password? Click here to reset