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 Cramér-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.
Prompting is not enough: supervised baselines and leakage control for measuring shared decision-making with LLMs in pediatric encounters
University of Utah（犹他大学）；University of Utah Spencer Fox Eccles School of Medicine（犹他大学斯宾塞·福克斯·埃克尔斯医学院）；Kahlert School of Computing, University of Utah（犹他大学卡勒特计算机学院）；Huntsman Cancer Institute, University of Utah（犹他大学亨茨曼癌症研究所）
PRIVET: PRoximIty leakage detection Via Extreme value Theory
Université Paris-Saclay（巴黎-萨克雷大学）；CNRS（法国国家科学研究中心）；INRIA（法国国家信息与自动化研究所）；Universidad Complutense de Madrid（马德里康普顿斯大学）；Universidad Politécnica de Madrid（马德里理工大学）；University of Tartu（塔尔图大学）
Category learning in deep neural networks: Information content and geometry of internal representations
Centre d’Analyse et de Mathématique Sociales (CAMS) EHESS, CNRS École des Hautes Études en Sciences Sociales（分析与数学社会中心（CAMS）EHESS，CNRS高等社会科学学院）；Laboratoire de Physique de l’École Normale Supérieure (LPENS), ENS, Université PSL, CNRS, Sorbonne Université, Université Paris Cité École Normale Supérieure（高等师范物理实验室（LPENS），ENS，PSL大学，CNRS，索邦大学，巴黎城市大学高等师范学院）
