Log In Sign Up

p-DkNN: Out-of-Distribution Detection Through Statistical Testing of Deep Representations

by   Adam Dziedzic, et al.

The lack of well-calibrated confidence estimates makes neural networks inadequate in safety-critical domains such as autonomous driving or healthcare. In these settings, having the ability to abstain from making a prediction on out-of-distribution (OOD) data can be as important as correctly classifying in-distribution data. We introduce p-DkNN, a novel inference procedure that takes a trained deep neural network and analyzes the similarity structures of its intermediate hidden representations to compute p-values associated with the end-to-end model prediction. The intuition is that statistical tests performed on latent representations can serve not only as a classifier, but also offer a statistically well-founded estimation of uncertainty. p-DkNN is scalable and leverages the composition of representations learned by hidden layers, which makes deep representation learning successful. Our theoretical analysis builds on Neyman-Pearson classification and connects it to recent advances in selective classification (reject option). We demonstrate advantageous trade-offs between abstaining from predicting on OOD inputs and maintaining high accuracy on in-distribution inputs. We find that p-DkNN forces adaptive attackers crafting adversarial examples, a form of worst-case OOD inputs, to introduce semantically meaningful changes to the inputs.


page 1

page 2

page 3

page 4


SelectiveNet: A Deep Neural Network with an Integrated Reject Option

We consider the problem of selective prediction (also known as reject op...

Towards Improved Testing For Deep Learning

The growing use of deep neural networks in safety-critical applications ...

What You See is Not What the Network Infers: Detecting Adversarial Examples Based on Semantic Contradiction

Adversarial examples (AEs) pose severe threats to the applications of de...

Ensemble Bayesian Decision Making with Redundant Deep Perceptual Control Policies

This work presents a novel ensemble of Bayesian Neural Networks (BNNs) f...

Detecting Anomalous Inputs to DNN Classifiers By Joint Statistical Testing at the Layers

Detecting anomalous inputs, such as adversarial and out-of-distribution ...

Provable Worst Case Guarantees for the Detection of Out-of-Distribution Data

Deep neural networks are known to be overconfident when applied to out-o...

Norm-Scaling for Out-of-Distribution Detection

Out-of-Distribution (OoD) inputs are examples that do not belong to the ...