An efficient scheme is introduced that extends the generalized membership inference attack to every point in a model's training data set. Our approach leverages data partitioning to create variable sized training sets for the reference models. We then train an attack model for every single training example for a reference model configuration based upon output for each individual point. This allows us to quantify the membership inference attack vulnerability of each training data point. Using this approach, we discovered that smaller amounts of reference model training data led to a stronger attack. Furthermore, the reference models do not need to be of the same architecture as the target model, providing additional attack efficiencies. The attack may also be performed by an adversary even when they do not have the complete original data set.
Client-specific Property Inference against Secure Aggregation in Federated Learning
CISPA Helmholtz Center for Information Security（CISPA赫尔姆霍茨信息安全中心）；Department of Networked Systems and Services, CrySyS Lab, BME（布达佩斯经济技术大学网络系统与服务系CrySyS实验室）
SMI: Statistical Membership Inference for Reliable Unlearned Model Auditing
Shenzhen University of Advanced Technology（深圳先进技术大学）；Peking University（北京大学）；Xi’an Jiaotong University（西安交通大学）；Heilongjiang University（黑龙江大学）；Stevens Institute of Technology（斯蒂文斯理工学院）
Trained Random Forests Completely Reveal your Dataset
CIRRELT；SCALE-AI Chair in Data-Driven Supply Chains（SCALE-AI数据驱动供应链讲席）；Polytechnique Montréal（蒙特利尔理工学院）；University of Waterloo（滑铁卢大学）；Ecole nationale des ponts et chaussées（巴黎路桥学院）
Using Decentralized Aggregation for Federated Learning with Differential Privacy
College of Computing and Information Technology, Arab Academy for Science, Technology, and Maritime Transport (AASTMT)（阿拉伯科学、技术与海运学院（AASTMT）计算与信息技术学院）；Universidade de Vigo（维戈大学）
Differentially private federated learning with Byzantine-robust aggregation: A cross-domain framework for secure model training in banking and healthcare systems
ICAS: Detecting Training Data from Autoregressive Image Generative Models
Tsinghua Shenzhen International Graduate School, Tsinghua University（清华大学深圳国际研究生院）；Harbin Institute of Technology, Shenzhen（哈尔滨工业大学深圳学院）；Shenzhen ShenNong Information Technology Co., Ltd.（深圳深农信息技术有限公司）
