Measuring Data Leakage in Machine-Learning Models with Fisher Information (Extended Abstract)
Measuring Data Leakage in Machine-Learning Models with Fisher Information (Extended Abstract)
Awni Hannun, Chuan Guo, Laurens van der Maaten
Proceedings of the Thirty-First International Joint Conference on Artificial Intelligence
Sister Conferences Best Papers. Pages 5284-5288.
https://doi.org/10.24963/ijcai.2022/736
Machine-learning models contain information about the data they were trained on. This information leaks either through the model itself or through predictions made by the model. Consequently, when the training data contains sensitive attributes, assessing the amount of information leakage is paramount. We propose a method to quantify this leakage using the Fisher information of the model about the data. Unlike the worst-case a priori guarantees of differential privacy, Fisher information loss measures leakage with respect to specific examples, attributes, or sub-populations within the dataset. We motivate Fisher information loss through the Cramer-Rao bound and delineate the implied threat model. We provide efficient methods to compute Fisher information loss for output-perturbed generalized linear models. Finally, we empirically validate Fisher information loss as a useful measure of information leakage.
Keywords:
Artificial Intelligence: General