Distributed machine learning generally aims at training a global model based on distributed data without collecting all the data to a centralized location, where two different approaches have been proposed: collecting and aggregating local models (federated learning) and collecting and training over representative data summaries (coreset). While each approach preserves data privacy to some extent thanks to not sharing the raw data, the exact extent of protection is unclear under sophisticated attacks that try to infer the raw data from the shared information. We present the first comparison between the two approaches in terms of target model accuracy, communication cost, and data privacy, where the last is measured by the accuracy of a state-of-the-art attack strategy called the membership inference attack. Our experiments quantify the accuracy-privacy-cost tradeoff of each approach, and reveal a nontrivial comparison that can be used to guide the design of model training processes.
Membership Inference Attacks on Deep Regression Models for Neuroimaging
Information Sciences Institute, University of Southern California(南加州大学信息科学研究所);Mark and Mary Stevens Institute for Neuroimaging and Informatics, Keck School of Medicine, University of Southern California(南加州大学凯克医学院马克与玛丽·史蒂文斯神经影像与信息学研究所);University of Southern California(南加州大学)
Toward Efficient Membership Inference Attacks against Federated Large Language Models: A Projection Residual Approach
Colleague of Computer Science and Technology, National University of Defense Technology, Changsha, China(计算机科学与技术系,国防科技大学,中国长沙);City University of Hong Kong, Hong Kong, China(香港城市大学,中国香港);Shenzhen University, Shenzhen, China(深圳大学,中国深圳)
When Privacy Isn't Synthetic: Hidden Data Leakage in Generative AI Models
Department of Mathematical Sciences University of Texas at El Paso(数学科学系德克萨斯理工大学埃尔帕索分校);Department of Computer Science University of Texas at El Paso(计算机科学系德克萨斯理工大学埃尔帕索分校);Department of Radiology St. Jude Children’s Research Hospital(放射医学系圣犹太儿童研究医院)
FedXDS: Leveraging Model Attribution Methods to counteract Data Heterogeneity in Federated Learning
Fraunhofer Heinrich Hertz Institute(弗劳恩霍夫海因里希·赫兹研究所);Technical University of Berlin(柏林工业大学);Berlin Institute for the Foundations of Learning and Data (BIFOLD)(柏林学习与数据基础研究所)
A Federated Parameter Aggregation Method for Node Classification Tasks with Different Graph Network Structures
Institute of Cyberspace Security, Zhejiang University of Technology(浙江工业大学网络空间安全研究院);Binjiang Cyberspace Security Institute of ZJUT(浙江工业大学滨江网络空间安全研究院);College of Information Engineering, Zhejiang University of Technology(浙江工业大学信息工程学院)
Defending Against Data Reconstruction Attacks in Federated Learning: An Information Theory Approach
Tsinghua University(清华大学);Institute for Network Science and Cyberspace, Tsinghua University(清华大学网络科学与网络空间研究院);Beijing Institute of Technology(北京理工大学);Lenovo Research(联想研究院)
University of Oxford(牛津大学);University of Cambridge(剑桥大学);University of California, Los Angeles(加利福尼亚大学洛杉矶分校);University of Waterloo(滑铁卢大学);Amsterdam UMC(阿姆斯特丹大学医学中心);Cambridge University Hospitals NHS Foundation Trust(剑桥大学医院NHS基金会信托);Microsoft Research(微软研究院);Alan Turing Institute(艾伦·图灵研究所)
Publishing Neural Networks in Drug Discovery Might Compromise Training Data Privacy
AstraZeneca R&D Discovery Sciences(阿斯利康研发部研发科学部);Technical University of Munich(慕尼黑工业大学);Helmholtz Munich(慕尼黑亥姆霍兹中心);AI Sweden(瑞典AI中心);Chalmers University of Technology(查尔姆斯理工大学)
Privacy-Preserving EHR Data Transformation via Geometric Operators: A Human-AI Co-Design Technical Report
Hong Kong Institute of AI for Science (HKAI-Sci), City University of Hong Kong(香港人工智能科学研究院(HKAI-Sci),香港城市大学);Department of Biostatistics, City University of Hong Kong(香港城市大学生物统计学系);Institute of Digital Medicine, City University of Hong Kong(香港城市大学数字医学研究院);YIDU TECH co. Ltd.(YIDU科技有限公司)
DP-TLDM: Differentially Private Tabular Latent Diffusion Model
TU Delft, Delft, Netherlands , University of Neuchâtel, Neuchâtel, Switzerland Universidad de los Andes, Bogotá, Colombia Centrum Wiskunde \& Informatica, Amsterdam, Netherlands
SNPgen: Phenotype-Supervised Genotype Representation and Synthetic Data Generation via Latent Diffusion
DEIB, Politecnico di Milano(米兰理工学院DEIB部门);Politecnico di Milano(米兰理工学院);Health Data Science Centre, Human Technopole(人类技术pole健康数据科学中心);Genomics Research Centre, Human Technopole(人类技术pole基因组研究中心);MOX - Department of Mathematics, Politecnico di Milano(米兰理工学院数学系);Department of Public Health and Primary Care, University of Cambridge(剑桥大学公共卫生与初级护理系)