# A general-purpose method for applying Explainable AI for Anomaly Detection

arXiv: https://arxiv.org/abs/2207.11564 · HTML: https://mlsanity.com/paper/2207.11564/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- Builds on 18 of its 38 references that are in the map.
- First posted on arXiv 23 Jul 2022.

## Builds on (most cited first, 18 of 18)

- [A Unified Approach to Interpreting Model Predictions](https://mlsanity.com/paper/1705.07874/) (2017)
- ["Why Should I Trust You?": Explaining the Predictions of Any Classifier](https://mlsanity.com/paper/1602.04938/) (2016)
- [Axiomatic Attribution for Deep Networks](https://mlsanity.com/paper/1703.01365/) (2017)
- [Learning Important Features Through Propagating Activation Differences](https://mlsanity.com/paper/1704.02685/) (2017)
- [Towards A Rigorous Science of Interpretable Machine Learning](https://mlsanity.com/paper/1702.08608/) (2017)
- [Explanation in Artificial Intelligence: Insights from the Social Sciences](https://mlsanity.com/paper/1706.07269/) (2017)
- [The Mythos of Model Interpretability](https://mlsanity.com/paper/1606.03490/) (2016)
- [A Unifying Review of Deep and Shallow Anomaly Detection](https://mlsanity.com/paper/2009.11732/) (2020)
- [The many Shapley values for model explanation](https://mlsanity.com/paper/1908.08474/) (2019)
- [Explainable Artificial Intelligence: Understanding, Visualizing and Interpreting Deep Learning Models](https://mlsanity.com/paper/1708.08296/) (2017)
- [Layer-wise Relevance Propagation for Neural Networks with Local Renormalization Layers](https://mlsanity.com/paper/1604.00825/) (2016)
- [Explainable Deep One-Class Classification](https://mlsanity.com/paper/2007.01760/) (2020)
- [Contrastive Explanation: A Structural-Model Approach](https://mlsanity.com/paper/1811.03163/) (2018)
- [Explanation Methods in Deep Learning: Users, Values, Concerns and Challenges](https://mlsanity.com/paper/1803.07517/) (2018)
- [Explaining Anomalies Detected by Autoencoders Using SHAP](https://mlsanity.com/paper/1903.02407/) (2019)
- [Interpretable, Multidimensional, Multimodal Anomaly Detection with Negative Sampling for Detection of Device Failure](https://mlsanity.com/paper/2007.10088/) (2020)
- [Towards Explaining Anomalies: A Deep Taylor Decomposition of One-Class Models](https://mlsanity.com/paper/1805.06230/) (2018)
- [The Explanation Game: Explaining Machine Learning Models Using Shapley Values](https://mlsanity.com/paper/1909.08128/) (2019)

## Built on by (most cited first, 7 of 7)

- [A Survey on Explainable Anomaly Detection](https://mlsanity.com/paper/2210.06959/) (2022)
- [LogicQA: Logical Anomaly Detection with Vision Language Model Generated Questions](https://mlsanity.com/paper/2503.20252/) (2025)
- [Generative Perturbation Analysis for Probabilistic Black-Box Anomaly Attribution](https://mlsanity.com/paper/2308.04708/) (2023)
- [Developing Guidelines for Functionally-Grounded Evaluation of Explainable Artificial Intelligence using Tabular Data](https://mlsanity.com/paper/2410.12803/) (2024)
- [Black-Box Anomaly Attribution](https://mlsanity.com/paper/2305.18440/) (2023)
- [Extending Decision Predicate Graphs for Comprehensive Explanation of Isolation Forest](https://mlsanity.com/paper/2505.04019/) (2025)
- [Detection of Sensor-To-Sensor Variations using Explainable AI](https://mlsanity.com/paper/2306.10850/) (2023)

## Abstract (arXiv)

The need for explainable AI (XAI) is well established but relatively little has been published outside of the supervised learning paradigm. This paper focuses on a principled approach to applying explainability and interpretability to the task of unsupervised anomaly detection. We argue that explainability is principally an algorithmic task and interpretability is principally a cognitive task, and draw on insights from the cognitive sciences to propose a general-purpose method for practical diagnosis using explained anomalies. We define Attribution Error, and demonstrate, using real-world labeled datasets, that our method based on Integrated Gradients (IG) yields significantly lower attribution errors than alternative methods.