Towards integration of Privacy Enhancing Technologies in Explainable Artificial Intelligence
Preprint
Abstract
Explainable Artificial Intelligence (XAI) is a crucial pathway in mitigating the risk of non-transparency in the decision-making process of black-box Artificial Intelligence (AI) systems. However, despite the benefits, XAI methods are found to leak the privacy of individuals whose data is used in training or querying the models. Researchers have demonstrated privacy attacks that exploit explanations to infer sensitive personal information of individuals. Currently there is a lack of defenses against known privacy attacks targeting explanations when vulnerable XAI are used in production and machine learning as a service system. To address this gap, in this article, we explore Privacy Enhancing Technologies (PETs) as a defense mechanism against attribute inference on explanations provided by feature-based XAI methods. We empirically evaluate 3 types of PETs, namely synthetic training data, differentially private training and noise addition, on two categories of feature-based XAI. Our evaluation determines different responses from the mitigation methods and side-effects of PETs on other system properties such as utility and performance. In the best case, PETs integration in explanations reduced the risk of the attack by 49.47%, while maintaining model utility and explanation quality. Through our evaluation, we identify strategies for using PETs in XAI for maximizing benefits and minimizing the success of this privacy attack on sensitive personal information.Keywords
All Related Versions
This publication has 68 references indexed in Scilit:
- Combinations of AI Models and XAI Metrics Vulnerable to Record Reconstruction Risk2024
- Privacy-Preserving AI Techniques2024
- Empirical Evaluation of Synthetic Data Created by Generative Models via Attribute Inference Attack2024
- Exploring Privacy-Preserving Techniques on Synthetic Data as a Defense Against Model Inversion Attacks2023
- Privacy-Preserving Machine Learning for Healthcare: Open Challenges and Future Perspectives2023
- DeepFixCX: Explainable privacy‐preserving image compression for medical image analysisWIREs Data Mining and Knowledge Discovery, 2023
- Towards explainable model extraction attacksInternational Journal of Intelligent Systems, 2022
- Blockchain for explainable and trustworthy artificial intelligenceWIREs Data Mining and Knowledge Discovery, 2019
- Our Data, Ourselves: Privacy Via Distributed Noise Generation2006
- On the Security of Noise Addition for Privacy in Statistical DatabasesLecture Notes in Computer Science, 2004