A Robust Likelihood Model for Novelty Detection

TL;DR

This paper introduces a new prior for likelihood estimation to enhance the robustness of novelty detection models against adversarial attacks, especially in unsupervised settings, with promising initial results.

Contribution

It proposes a novel prior for robust likelihood learning and integrates it with existing novelty detection methods to improve attack resilience.

Findings

Improved detection performance without attacks

Enhanced robustness against adversarial data

Computationally efficient training process

Abstract

Current approaches to novelty or anomaly detection are based on deep neural networks. Despite their effectiveness, neural networks are also vulnerable to imperceptible deformations of the input data. This is a serious issue in critical applications, or when data alterations are generated by an adversarial attack. While this is a known problem that has been studied in recent years for the case of supervised learning, the case of novelty detection has received very limited attention. Indeed, in this latter setting the learning is typically unsupervised because outlier data is not available during training, and new approaches for this case need to be investigated. We propose a new prior that aims at learning a robust likelihood for the novelty test, as a defense against attacks. We also integrate the same prior with a state-of-the-art novelty detection approach. Because of the geometric properties of that approach, the resulting robust training is computationally very efficient. An initial evaluation of the method indicates that it is effective at improving performance with respect to the standard models in the absence and presence of attacks.