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

Mohit Kumar, Bernhard A. Moser, Lukas Fischer, Bernhard Freudenthaler
2022 arXiv   pre-print
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
more » ... 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.
arXiv:2106.06046v5 fatcat:lm4irfkervgilds6ly65c624vq