# Differential Privacy for Anomaly Detection: Analyzing the Trade-off Between Privacy and Explainability

arXiv: https://arxiv.org/abs/2404.06144 · HTML: https://mlsanity.com/paper/2404.06144/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 14 of its 57 references that are in the map.
- First posted on arXiv 9 Apr 2024.

## Builds on (most cited first, 14 of 14)

- [A Unified Approach to Interpreting Model Predictions](https://mlsanity.com/paper/1705.07874/) (2017)
- [Deep Learning with Differential Privacy](https://mlsanity.com/paper/1607.00133/) (2016)
- [A Survey Of Methods For Explaining Black Box Models](https://mlsanity.com/paper/1802.01933/) (2018)
- [Deep Anomaly Detection with Deviation Networks](https://mlsanity.com/paper/1911.08623/) (2019)
- [Robust Anomaly Detection and Backdoor Attack Detection Via Differential Privacy](https://mlsanity.com/paper/1911.07116/) (2019)
- [Interpretable and Differentially Private Predictions](https://mlsanity.com/paper/1906.02004/) (2019)
- [Accuracy, Interpretability, and Differential Privacy via Explainable Boosting](https://mlsanity.com/paper/2106.09680/) (2021)
- [Utilizing XAI technique to improve autoencoder based model for computer network anomaly detection with shapley additive explanation(SHAP)](https://mlsanity.com/paper/2112.08442/) (2021)
- [The Tradeoff Between Privacy and Accuracy in Anomaly Detection Using Federated XGBoost](https://mlsanity.com/paper/1907.07157/) (2019)
- [Using Kernel SHAP XAI Method to optimize the Network Anomaly Detection Model](https://mlsanity.com/paper/2308.00074/) (2023)
- [When Differential Privacy Meets Interpretability: A Case Study](https://mlsanity.com/paper/2106.13203/) (2021)
- [Differentially Private Analysis of Outliers](https://mlsanity.com/paper/1507.06763/) (2015)
- [Trustworthy Anomaly Detection: A Survey](https://mlsanity.com/paper/2202.07787/) (2022)
- [Privacy-preserving Anomaly Detection in Cloud Manufacturing via Federated Transformer](https://mlsanity.com/paper/2204.00843/) (2022)

## Built on by (most cited first, 2 of 2)

- [Privacy Risks and Preservation Methods in Explainable Artificial Intelligence: A Scoping Review](https://mlsanity.com/paper/2505.02828/) (2025)
- [Explanations Leak: Membership Inference with Differential Privacy and Active Learning Defense](https://mlsanity.com/paper/2602.03611/) (2026)

## Abstract (arXiv)

Anomaly detection (AD), also referred to as outlier detection, is a statistical process aimed at identifying observations within a dataset that significantly deviate from the expected pattern of the majority of the data. Such a process finds wide application in various fields, such as finance and healthcare. While the primary objective of AD is to yield high detection accuracy, the requirements of explainability and privacy are also paramount. The first ensures the transparency of the AD process, while the second guarantees that no sensitive information is leaked to untrusted parties. In this work, we exploit the trade-off of applying Explainable AI (XAI) through SHapley Additive exPlanations (SHAP) and differential privacy (DP). We perform AD with different models and on various datasets, and we thoroughly evaluate the cost of privacy in terms of decreased accuracy and explainability. Our results show that the enforcement of privacy through DP has a significant impact on detection accuracy and explainability, which depends on both the dataset and the considered AD model. We further show that the visual interpretation of explanations is also influenced by the choice of the AD algorithm.