Differential privacy (DP) ensures rigorous individual-level privacy guarantees against even the most knowledgeable attackers, but its worst-case nature can impose a costly privacy-accuracy tradeoff. We introduce privacy via predictability, a fine-grained framework that explicitly incorporates the attacker's core knowledge, a compromised portion of the dataset generated by a stochastic process, and a specified family of queries. Predictability measures privacy leakage as the incremental gain in an attacker's ability to predict sensitive information about unknown individuals after observing the algorithm's output, beyond what can already be inferred from the compromised data. We show that predictability and DP are generally incomparable: each can be small while the other is large. However, in the worst-case regime where all but one individual is compromised, and all binary queries are considered sensitive, predictability implies mutual-information DP. More generally, predictability provides a finer-grained privacy metric tailored to specific sensitive information and specific attacker models. We introduce a general framework, using the generalized method of moments (GMM), to analyze asymptotic predictability when the compromised data is generated by a stationary, ergodic, mixing process. Using this analysis, we derive a predictability-calibrated output perturbation scheme for ERM. Our approach is complementary to DP and can be used alongside DP to provide fine-grained privacy control.
Machine unlearning through fine-grained model parameters perturbation
College of Computer Science and Electronic Engineering, Hunan University(湖南大学计算机与电子工程学院);College of Computing and Data Science, Nanyang Technological University(南洋理工大学计算与数据科学学院);Shenzhen Research Institute, Hunan University(湖南大学深圳研究院);Faculty of Computing, Engineering & Media, De Montfort University(德蒙福特大学计算、工程与媒体学院)
Theoretically Principled Federated Learning for Balancing Privacy and Utility
Huazhong University of Science and Technology(华中科技大学);Tsinghua University(清华大学);Peng Cheng Laboratory(鹏城实验室);WeBank(微众银行);The Hong Kong Polytechnic University(香港理工大学)
Free Lunch for Federated Remote Sensing Target Fine-Grained Classification: A Parameter-Efficient Framework
Guangdong-Hongkong-Macao Greater Bay Area Weather Research Center for Monitoring Warning and Forecasting (Shenzhen Institute of Meteorological Innovation)(粤港澳大湾区气象监测预警预报中心(深圳气象创新研究院));Australian Artificial Intelligence Institute, FEIT, University of Technology Sydney(悉尼科技大学工程与信息技术学院澳大利亚人工智能研究所);School of Electrical and Electronic Engineering, Nanyang Technological University(南洋理工大学电气与电子工程学院);School of Information and Communication Engineering, Hainan University(海南大学信息与通信工程学院);School of Computer, Electronics and Information, Guangxi University(广西大学计算机与电子信息学院)
Convergent Differential Privacy Analysis for General Federated Learning
School of Computer Science Faculty of Engineering(计算机科学学院工程学院);University of Sydney(悉尼大学);Generative AI Lab(生成式人工智能实验室);College of Computing and Data Science(计算与数据科学学院);Nanyang Technological University(南洋理工大学);School of Cyber Science and Technology(网络安全科学与技术学院);Shenzhen Campus of Sun Yat-sen University(中山大学深圳校区)
A New Perspective on Privacy Protection in Federated Learning with Granular-Ball Computing
Southwestern University of Finance and Economics(西南财经大学);Chongqing University of Posts and Telecommunications(重庆邮电大学);Southwest Jiaotong University(西南交通大学)
Demographic Predictability in 3D CT Foundation Embeddings
Rice University(莱斯大学);McGovern Medical School, UTHealth Houston(德克萨斯大学休斯顿健康科学中心麦戈文医学院);Johns Hopkins University School of Medicine(约翰霍普金斯大学医学院);University of Maryland School of Medicine(马里兰大学医学院)
TimeGNN-Augmented Hybrid-Action MARL for Fine-Grained Task Partitioning and Energy-Aware Offloading in MEC
College of Computer and Mathematics(计算机与数学学院);Central South University of Forestry and Technology(林业与技术中央南大学);Department of Computer Science(计算机科学系);State University of New York(纽约州立大学)
Real-Time Privacy-Preserving Data Release for Smart Meters
McGill University(麦吉尔大学);CentraleSupélec(中央理工-高等电力学院);CNRS(法国国家科学研究中心);Université Paris Sud(巴黎第十一大学);Montreal Institute for Learning Algorithms (Mila)(蒙特利尔学习算法研究所);Université de Montréal(蒙特利尔大学)