Language selection

Government of Canada / Gouvernement du Canada

Search

Privacy-preserving explainable AIoT application via SHAP entropy regularization

DOIResolve DOI: https://doi.org/10.1109/AIoT66900.2025.00046
AuthorSearch for: 1; Search for: 1; Search for: 1; Search for: 2; Search for: 3ORCID identifier: https://orcid.org/0000-0002-3460-6946
Affiliation
  1. York University
  2. University of Guelph
  3. National Research Council Canada. Digital Technologies
FormatText, Article
Conference2025 IEEE Annual Congress on Artificial Intelligence of Things (AIoT), December 3-5, 2025, Osaka, Japan
Subjectprivacy; explainable AI; privacy-preserving explanations; privacy risk; membership inference; SHAP entropy regularization; trustworthy AI; smart home application; artificial intelligence of things
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.
Date published
PublisherInstitute of Electrical and Electronics Engineers
In
  • 2025 IEEE Annual Congress on Artificial Intelligence of Things (AIoT), 11416471 (9 March 2026): 253–261.
LanguageEnglish
Peer reviewedYes
Export citationExport as RIS
Report a correctionReport a correction (opens in a new tab)
Record identifierae58f920-a021-4c4d-97a4-0cac05e354a1
Record created2026-04-16
Record modified2026-06-08

Page details

From:

Date modified: