Privacy-Preserving Explainable AIoT Application via SHAP Entropy Regularization

TL;DR

This paper introduces a novel SHAP entropy regularization method to enhance privacy in explainable AIoT applications, effectively reducing privacy risks while maintaining model accuracy and interpretability.

Contribution

It proposes a new entropy-based regularization technique that mitigates privacy leakage in SHAP explanations for AIoT systems, a novel approach in privacy-preserving XAI.

Findings

Significantly reduces privacy leakage compared to baseline models.

Maintains high predictive accuracy and explanation fidelity.

Effective against SHAP-based privacy attacks.

Abstract

The widespread integration of Artificial Intelligence of Things (AIoT) in smart home environments has amplified the demand for transparent and interpretable machine learning models. To foster user trust and comply with emerging regulatory frameworks, the Explainable AI (XAI) methods, particularly post-hoc techniques such as SHapley Additive exPlanations (SHAP), and Local Interpretable Model-Agnostic Explanations (LIME), are widely employed to elucidate model behavior. However, recent studies have shown that these explanation methods can inadvertently expose sensitive user attributes and behavioral patterns, thereby introducing new privacy risks. To address these concerns, we propose a novel privacy-preserving approach based on SHAP entropy regularization to mitigate privacy leakage in explainable AIoT applications. Our method incorporates an entropy-based regularization objective that penalizes low-entropy SHAP attribution distributions during training, promoting a more uniform spread of feature contributions. To evaluate the effectiveness of our approach, we developed a suite of SHAP-based privacy attacks that strategically leverage model explanation outputs to infer sensitive information. We validate our method through comparative evaluations using these attacks alongside utility metrics on benchmark smart home energy consumption datasets. Experimental results demonstrate that SHAP entropy regularization substantially reduces privacy leakage compared to baseline models, while maintaining high predictive accuracy and faithful explanation fidelity. This work contributes to the development of privacy-preserving explainable AI techniques for secure and trustworthy AIoT applications.