Explainable machine learning models with privacy
Progress in Artificial Intelligence · 2024-03 · 13 (1) · 31-50
DOI: 10.1007/s13748-024-00315-2 ↗Kurz gefasst
Fachartikel in der Zeitschrift Progress in Artificial Intelligence, online erschienen am 28.03.2024. Verfasst von Aso Bozorgpanah und 1 weiteren Autor:innen. Die Arbeit wurde bisher 24-mal zitiert (Crossref) und nennt 44 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Knut och Alice Wallenbergs Stiftelse.
Abstract (Originalsprache)
The importance of explainable machine learning models is increasing because users want to understand the reasons behind decisions in data-driven models. Interpretability and explainability emerge from this need to design comprehensible systems. This paper focuses on privacy-preserving explainable machine learning. We study two data masking techniques: maximum distance to average vector (MDAV) and additive noise. The former is for achieving k -anonymity, and the second uses Laplacian noise to avoid record leakage and provide a level of differential privacy. We are interested in the process of developing data-driven models that, at the same time, make explainable decisions and are privacy-preserving. That is, we want to avoid the decision-making process leading to disclosure. To that end, we propose building models from anonymized data. More particularly, data that are k -anonymous or that have been anonymized add an appropriate level of noise to satisfy some differential privacy requirements. In this paper, we study how explainability has been affected by these data protection procedures. We use TreeSHAP as our technique for explainability. The experiments show that we can keep up to a certain degree both accuracy and explainability. So, our results show that some trade-off between privacy and explainability is possible for data protection using k -anonymity and noise addition.
Förderung
- Knut och Alice Wallenbergs Stiftelse
Zitieren
APA
Bozorgpanah, A., & Torra, V. (2024). Explainable machine learning models with privacy. Progress in Artificial Intelligence, 13(1), 31-50. https://doi.org/10.1007/s13748-024-00315-2
Vancouver
Bozorgpanah A, Torra V. Explainable machine learning models with privacy. Progress in Artificial Intelligence. 2024;13(1):31-50. doi:10.1007/s13748-024-00315-2
BibTeX
@article{Bozorgpanah2024,
author = {Bozorgpanah, Aso and Torra, Vicenç},
title = {Explainable machine learning models with privacy},
journal = {Progress in Artificial Intelligence},
year = {2024},
volume = {13},
number = {1},
pages = {31--50},
doi = {10.1007/s13748-024-00315-2}
}
EUVIMED