Information Theoretic Evaluation of Privacy-Leakage, Interpretability, and Transferability for Trustworthy AI
This work addresses the need for rigorous analytical methods to evaluate and balance key aspects of trustworthy AI, such as privacy and interpretability, which is important for researchers and practitioners in AI ethics and safety, though it appears incremental in combining existing concepts.
The authors tackled the challenge of developing trustworthy AI by introducing a novel information theoretic framework to study and optimize tradeoffs between privacy, interpretability, and transferability, demonstrating it through experiments on benchmark datasets and a real-world biomedical application for mental stress detection.
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.