loading
Papers Papers/2022 Papers Papers/2022

Research.Publish.Connect.

Paper

The Explainability-Privacy-Utility Trade-Off for Machine Learning-Based Tabular Data Analysis

Topics: Anonymity; Data Protection; Ethical and Legal Implications of Security and Privacy; Machine Learning and AI Security; Personal Data Protection for Information Systems; Privacy; Privacy Enhancing Technologies; Security and Privacy for Big Data; Security and Privacy in Complex Systems

Authors: Wisam Abbasi ; Paolo Mori and Andrea Saracino

Affiliation: Istituto di Informatica e Telematica, Consiglio Nazionale delle Ricerche, Pisa, Italy

Keyword(s): Data Privacy, Data Utility, Explainable AI, Privacy-Preserving Data Analysis, Trustworthy AI.

Abstract: In this paper, we present a novel privacy-preserving data analysis model, based on machine learning, applied to tabular datasets, which defines a general trade-off optimization criterion among the measures of data privacy, model explainability, and data utility, aiming at finding the optimal compromise among them. Our approach regulates the privacy parameter of the privacy-preserving mechanism used for the applied analysis algorithms and explainability techniques. Then, our method explores all possible configurations for the provided privacy parameter and manages to find the optimal configuration with the maximum achievable privacy gain and explainability similarity while minimizing harm to data utility. To validate our methodology, we conducted experiments using multiple classifiers for a binary classification problem on the Adult dataset, a well-known tabular dataset with sensitive attributes. We used (ε,δ)-differential privacy as a privacy mechanism and multiple model explanation methods. The results demonstrate the effectiveness of our approach in selecting an optimal configuration, that achieves the dual objective of safeguarding data privacy and providing model explanations of comparable quality to those generated from real data. Furthermore, the proposed method was able to preserve the quality of analyzed data, leading to accurate predictions. (More)

CC BY-NC-ND 4.0

Sign In Guest: Register as new SciTePress user now for free.

Sign In SciTePress user: please login.

PDF ImageMy Papers

You are not signed in, therefore limits apply to your IP address 3.129.249.170

In the current month:
Recent papers: 100 available of 100 total
2+ years older papers: 200 available of 200 total

Paper citation in several formats:
Abbasi, W.; Mori, P. and Saracino, A. (2023). The Explainability-Privacy-Utility Trade-Off for Machine Learning-Based Tabular Data Analysis. In Proceedings of the 20th International Conference on Security and Cryptography - SECRYPT; ISBN 978-989-758-666-8; ISSN 2184-7711, SciTePress, pages 511-519. DOI: 10.5220/0012137800003555

@conference{secrypt23,
author={Wisam Abbasi. and Paolo Mori. and Andrea Saracino.},
title={The Explainability-Privacy-Utility Trade-Off for Machine Learning-Based Tabular Data Analysis},
booktitle={Proceedings of the 20th International Conference on Security and Cryptography - SECRYPT},
year={2023},
pages={511-519},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0012137800003555},
isbn={978-989-758-666-8},
issn={2184-7711},
}

TY - CONF

JO - Proceedings of the 20th International Conference on Security and Cryptography - SECRYPT
TI - The Explainability-Privacy-Utility Trade-Off for Machine Learning-Based Tabular Data Analysis
SN - 978-989-758-666-8
IS - 2184-7711
AU - Abbasi, W.
AU - Mori, P.
AU - Saracino, A.
PY - 2023
SP - 511
EP - 519
DO - 10.5220/0012137800003555
PB - SciTePress