Adversarially Robust Industrial Anomaly Detection Through Diffusion Model

TL;DR

This paper introduces AdvRAD, a diffusion-based method that performs simultaneous anomaly detection and adversarial purification, achieving high robustness and detection accuracy in industrial settings.

Contribution

It proposes a novel diffusion model approach that combines anomaly detection with adversarial purification, extending to certified robustness against $l_2$ perturbations.

Findings

Outperforms state-of-the-art methods in robustness and detection accuracy

Achieves certified robustness against $l_2$ norm bounded attacks

Maintains high anomaly detection performance on benchmark datasets

Abstract

Deep learning-based industrial anomaly detection models have achieved remarkably high accuracy on commonly used benchmark datasets. However, the robustness of those models may not be satisfactory due to the existence of adversarial examples, which pose significant threats to the practical deployment of deep anomaly detectors. Recently, it has been shown that diffusion models can be used to purify the adversarial noises and thus build a robust classifier against adversarial attacks. Unfortunately, we found that naively applying this strategy in anomaly detection (i.e., placing a purifier before an anomaly detector) will suffer from a high anomaly miss rate since the purifying process can easily remove both the anomaly signal and the adversarial perturbations, causing the later anomaly detector failed to detect anomalies. To tackle this issue, we explore the possibility of performing anomaly detection and adversarial purification simultaneously. We propose a simple yet effective adversarially robust anomaly detection method, \textit{AdvRAD}, that allows the diffusion model to act both as an anomaly detector and adversarial purifier. We also extend our proposed method for certified robustness to $l_2$ norm bounded perturbations. Through extensive experiments, we show that our proposed method exhibits outstanding (certified) adversarial robustness while also maintaining equally strong anomaly detection performance on par with the state-of-the-art methods on industrial anomaly detection benchmark datasets.