Reverse KL-Divergence Training of Prior Networks: Improved Uncertainty and Adversarial Robustness

By Andrey Malinin, Mark John Francis Gales. 2019

227 citations recorded by the source corpus.

Ensemble approaches for uncertainty estimation have recently been applied to the tasks of misclassification detection, out-of-distribution input detection and adversarial attack detection. Prior Networks have been proposed as an approach to efficiently \emph{emulate} an ensemble of models for classification by parameterising a Dirichlet prior distribution over output distributions. These models have been shown to outperform alternative ensemble approaches, such as Monte-Carlo Dropout, on the task of out-of-distribution input detection. However, scaling Prior Networks to complex datasets with many classes is difficult using the training criteria originally proposed. This paper makes two contributions. First, we show that the appropriate training criterion for Prior Networks is the \emph{reverse} KL-divergence between Dirichlet distributions. This addresses issues in the nature of the training data target distributions, enabling prior networks to be successfully trained on classification tasks with arbitrarily many classes, as well as improving out-of-distribution detection performance. Second, taking advantage of this new training criterion, this paper investigates using Prior Networks to detect adversarial attacks and proposes a generalized form of adversarial training. It is shown that the construction of successful \emph{adaptive} whitebox attacks, which affect the prediction and evade detection, against Prior Networks trained on CIFAR-10 and CIFAR-100 using the proposed approach requires a greater amount of computational effort than against networks defended using standard adversarial training or MC-dropout.

Subfields: Artificial Intelligence, Molecular Biology

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Molecular Biology

Citations in the corpus

A Review of Uncertainty Quantification in Deep Learning: Techniques, Applications and Challenges (2020, background): “[313], Malinin and Gales [314], Jain et al.”
Generalized Out-of-Distribution Detection: A Survey (2021, unknown): “Dirichlet Prior Network (DPN) is also used for OOD detection with an uncertainty modeling of three different sources of uncertainty: model uncertainty, data uncertainty, and distributional uncertainty, and form a line of works (Malinin & Gales, 2018, 2019; Nandy et al., 2020).”
Deep Evidential Regression (2019, methodology): “Our methodology closely relates to evidential deep learning [42] and Prior Networks [32, 33] which place Dirichlet priors over discrete classification predictions.”
A survey of uncertainty in deep neural networks (2021, background): “total sum of the (exponentials of) the logits as precision value of a Dirichlet distribution (see description of Dirichlet Priors in Section III-A) [32], [94], [64], or as a collection of evidence that is compared to a defined constant [44], [92].”