In this paper, we develop a series of differential privacy (DP) algorithms from a family of random projections (RP) for general applications in machine learning, data mining, and information retrieval. Among the presented algorithms, iDP-SignRP is remarkably effective under the setting of ``individual differential privacy'' (iDP), based on sign random projections (SignRP). Also, DP-SignOPORP considerably improves existing algorithms in the literature under the standard DP setting, using ``one permutation + one random projection'' (OPORP), where OPORP is a variant of the celebrated count-sketch method with fixed-length binning and normalization. Without taking signs, among the DP-RP family, DP-OPORP achieves the best performance.
Our key idea for improving DP-RP is to take only the signs, i.e., $sign(x_j) = sign\left(\sum_{i=1}^p u_i w_{ij}\right)$, of the projected data. The intuition is that the signs often remain unchanged when the original data ($u$) exhibit small changes (according to the ``neighbor'' definition in DP). In other words, the aggregation and quantization operations themselves provide good privacy protections. We develop a technique called ``smooth flipping probability'' that incorporates this intuitive privacy benefit of SignRPs and improves the standard DP bit flipping strategy. Based on this technique, we propose DP-SignOPORP which satisfies strict DP and outperforms other DP variants based on SignRP (and RP), especially when $ε$ is not very large (e.g., $ε= 5\sim10$). Moreover, if an application scenario accepts individual DP, then we immediately obtain an algorithm named iDP-SignRP which achieves excellent utilities even at small~$ε$ (e.g., $ε<0.5$).
TriShield: Zero-Utility-Loss Defense Against Privacy Backdoors in Federated Language Model Fine-Tuning via Orthogonal Gradient Projection and Optimizer State Entanglement
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）
Helsinki Institute for Information Technology HIIT（赫尔辛基信息技术研究所）；University of Helsinki（赫尔辛基大学）；Waseda University（早稻田大学）；Aalto University（阿尔托大学）；University of Manchester（曼彻斯特大学）
An exponential mechanism based on quadratic approximations for fine-tuning machine learning models with privacy guarantees
Computer Science and Mathematics Division, Oak Ridge National Laboratory（橡树岭国家实验室计算机科学与数学 division）；Computational Science and Engineering Division, Oak Ridge National Laboratory（橡树岭国家实验室计算科学与工程 division）；HPC Department, Cineca（Cineca 高性能计算部）
GCFL: A Gradient Correction-based Federated Learning Framework for Privacy-preserving CPSS
School of Software Engineering, Nanjing University of Information Science and Technology（南京信息工程大学软件学院）；College of Meteorology and Oceanography, National University of Defense Technology（国防科技大学气象海洋学院）；CSIRO’s Data61（澳大利亚CSIRO数据61研究所）；Medical Sciences Division, University of Oxford（牛津大学医学科学学院）；Jiangsu Province Engineering Research Center of Advanced Computing and Intelligent Services（江苏省先进计算与智能服务工程研究中心）；Jiangsu Collaborative Innovation Center of Atmospheric Environment and Equipment Technology（江苏省大气环境与装备技术协同创新中心）；Nanjing University of Information Science and Technology（南京信息工程大学）；State Key Laboratory for Novel Software Technology, Nanjing University（南京大学新型软件技术国家重点实验室）
Privacy-Preserving Transfer Learning for Community Detection using Locally Distributed Multiple Networks
School of Mathematics, Northwest University, China（西北大学数学学院，中国）；Department of Statistics and Data Science, Washington University in St. Louis, U.S.A.（圣路易斯华盛顿大学统计与数据科学系，美国）；School of Management, Xi’an Jiaotong University, China（西安交通大学管理学院，中国）
ScoreShield: Differentially Private Release of Similarity Scores
School of Engineering and Applied Sciences, Harvard University（哈佛大学工程与应用科学学院）；School of Engineering, École Polytechnique Fédérale de Lausanne (EPFL)（洛桑联邦理工学院工程学院）
Differentially Private Model-X Knockoffs via Johnson-Lindenstrauss Transform
Department of Mathematics, University of Southern California（数学系，南加州大学）；Department of Data Sciences and Operations, University of Southern California（数据科学与运营系，南加州大学）
Federated Learning on Riemannian Manifolds: A Gradient-Free Projection-Based Approach
School of Information Management and Engineering, Shanghai University of Finance and Economics（上海金融学院信息管理与工程学院）；School of Information Management and Engineering, Shanghai University of Finance and Economics（上海金融学院信息管理与工程学院；明尼苏达大学工业与系统工程系）；Department of Industrial and System Engineering, University of Minnesota（明尼苏达大学电气与计算机工程系）；Department of Electrical and Computer Engineering, University of Minnesota
Data Obfuscation through Latent Space Projection (LSP) for Privacy-Preserving AI Governance: Case Studies in Medical Diagnosis and Finance Fraud Detection
Adversarial Signed Graph Learning with Differential Privacy
The Hong Kong Polytechnic University（香港理工大学）；Research Centre for Privacy and Security Technologies in Future Smart Systems, PolyU（隐私与安全技术在未来智能系统中的研究中心，PolyU）
