# Privacy-Preserving Explainable AIoT Application via SHAP Entropy Regularization

arXiv: https://arxiv.org/abs/2511.09775 · HTML: https://mlsanity.com/paper/2511.09775/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 17 of its 54 references that are in the map.
- First posted on arXiv 12 Nov 2025.

## Builds on (most cited first, 17 of 17)

- [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)
- [Opacus: User-Friendly Differential Privacy Library in PyTorch](https://mlsanity.com/paper/2109.12298/) (2021)
- [Chasing Your Long Tails: Differentially Private Prediction in Health Care Settings](https://mlsanity.com/paper/2010.06667/) (2020)
- [Interpretable and Differentially Private Predictions](https://mlsanity.com/paper/1906.02004/) (2019)
- [The privacy issue of counterfactual explanations: explanation linkage attacks](https://mlsanity.com/paper/2210.12051/) (2022)
- [On the Privacy Effect of Data Enhancement via the Lens of Memorization](https://mlsanity.com/paper/2208.08270/) (2022)
- [Explainable Activity Recognition for Smart Home Systems](https://mlsanity.com/paper/2105.09787/) (2021)
- [Improving Robustness with Adaptive Weight Decay](https://mlsanity.com/paper/2210.00094/) (2022)
- [Artificial Intelligence of Things: A Survey](https://mlsanity.com/paper/2410.19998/) (2024)
- [XRand: Differentially Private Defense against Explanation-Guided Attacks](https://mlsanity.com/paper/2212.04454/) (2022)
- [A Survey on Intelligent Internet of Things: Applications, Security, Privacy, and Future Directions](https://mlsanity.com/paper/2406.03820/) (2024)
- [Feature Inference Attack on Shapley Values](https://mlsanity.com/paper/2407.11359/) (2024)
- [On the amplification of security and privacy risks by post-hoc explanations in machine learning models](https://mlsanity.com/paper/2206.14004/) (2022)
- [Accurate, Explainable, and Private Models: Providing Recourse While Minimizing Training Data Leakage](https://mlsanity.com/paper/2308.04341/) (2023)
- [Privacy Preserving Demand Forecasting to Encourage Consumer Acceptance of Smart Energy Meters](https://mlsanity.com/paper/2012.07449/) (2020)
- [Towards integration of Privacy Enhancing Technologies in Explainable Artificial Intelligence](https://mlsanity.com/paper/2507.04528/) (2025)

## Built on by (most cited first, 1 of 1)

- [Mitigating Explanation Leakage in Financial Fraud Detection Systems](https://mlsanity.com/paper/2608.22607/) (2026)

## Abstract (arXiv)

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.