General Frameworks for Anomaly Detection Explainability: Comparative Study

Feature relevance XAI in anomaly detection: Reviewing approaches and challenges

“…The defects are annotated with manually created ground truth pixel maps, with binary indications of pixels that are part of the defect. The dataset has been previously used to evaluate feature relevance XAI approaches by Ravi et al ( 2021 ), although their evaluations are limited to qualitative inspections of results. To instead generate quantitative results of XAI performance, we use the ground truth anomaly segmentation maps as ground truths for explanations.…”

“…For the ERP dataset, Tritscher et al ( 2022b ) conduct a hyperparameter study of multiple anomaly detectors on the data, finding architectures that yield good results on the dataset. For our showcases, we select their second best performing model, the autoencoder neural network (Goodfellow et al, 2016 ) architecture, with their found hyperparameters as they show that their best performing one-class support vector machine (Schölkopf et al, 2001 ) exibits an erratic decision process that may influence a quantitative XAI evaluation and autoencoder networks are commonly studied in the domain of explainable anomaly detection (Antwarg et al, 2021 ; Ravi et al, 2021 ; Müller et al, 2022 ).…”

“…For datasets with high dimensionality d and a known hierarchy between dimensions (e.g., local dependencies in images), "partition-SHAP" extends this approach to groups of features through the gametheoretic extensions to Owen values (Owen, 1977) and achieves faster run times as a result. Shapley value explanations are some of the most used approaches in anomaly detection, with multiple applications on reconstructionbased anomaly detectors such as autoencoder neural networks (Antwarg et al, 2021;Ravi et al, 2021;Müller et al, 2022;Tritscher et al, 2022b). While Ravi et al (2021) and Tritscher et al (2022b) apply Shapley value estimation directly on the final anomaly score of the reconstruction-based anomaly detection model, Antwarg et al (2021) first identify the features with highest reconstruction errors and apply kernel-SHAP directly on the most deviating features.…”

“…Ravi et al ( 2021 ) directly apply LIME on the anomaly detection MVTec dataset with a brief qualitative demonstration of results. Further, Zhang et al ( 2019 ) apply LIME on multiple anomaly detection datasets from the security domain that focus on intrusion and malware detection.…”

“…Shapley value explanations are some of the most used approaches in anomaly detection, with multiple applications on reconstruction-based anomaly detectors such as autoencoder neural networks (Antwarg et al, 2021 ; Ravi et al, 2021 ; Müller et al, 2022 ; Tritscher et al, 2022b ). While Ravi et al ( 2021 ) and Tritscher et al ( 2022b ) apply Shapley value estimation directly on the final anomaly score of the reconstruction-based anomaly detection model, Antwarg et al ( 2021 ) first identify the features with highest reconstruction errors and apply kernel-SHAP directly on the most deviating features. Müller et al ( 2022 ) further extend this approach to categorical one-hot encoded data by averaging over groups of one-hot encoded features.…”