Information Theoretic Evaluation of Privacy-Leakage, Interpretability, and Transferability for Trustworthy AI

Authors: Mohit Kumar, Bernhard A. Moser, Lukas Fischer, Bernhard Freudenthaler
Published: 2021-06-06 | Updated: 2022-04-12

Source: https://arxiv.org/abs/2106.06046

PDF: https://arxiv.org/pdf/2106.06046

AIにより推定されたラベル

プライバシー保護技術 情報理論的評価 データ漏洩

※ こちらのラベルはAIによって自動的に追加されました。そのため、正確でないことがあります。
詳細は文献データベースについてをご覧ください。

Abstract

In order to develop machine learning and deep learning models that take into account the guidelines and principles of trustworthy AI, a novel information theoretic trustworthy AI framework is introduced. A unified approach to “privacy-preserving interpretable and transferable learning” is considered for studying and optimizing the tradeoffs between privacy, interpretability, and transferability aspects. A variational membership-mapping Bayesian model is used for the analytical approximations of the defined information theoretic measures for privacy-leakage, interpretability, and transferability. The approach consists of approximating the information theoretic measures via maximizing a lower-bound using variational optimization. The study presents a unified information theoretic approach to study different aspects of trustworthy AI in a rigorous analytical manner. The approach is demonstrated through numerous experiments on benchmark datasets and a real-world biomedical application concerned with the detection of mental stress on individuals using heart rate variability analysis.