The recently proposed Fast Fourier Transform (FFT)-based accountant for evaluating $(\varepsilon,δ)$-differential privacy guarantees using the privacy loss distribution formalism has been shown to give tighter bounds than commonly used methods such as Rényi accountants when applied to homogeneous compositions, i.e., to compositions of identical mechanisms. In this paper, we extend this approach to heterogeneous compositions. We carry out a full error analysis that allows choosing the parameters of the algorithm such that a desired accuracy is obtained. The analysis also extends previous results by taking into account all the parameters of the algorithm. Using the error analysis, we also give a bound for the computational complexity in terms of the error which is analogous to and slightly tightens the one given by Murtagh and Vadhan (2018). We also show how to speed up the evaluation of tight privacy guarantees using the Plancherel theorem at the cost of increased pre-computation and memory usage.
Helsinki Institute for Information Technology HIIT（赫尔辛基信息技术研究所HIIT）；University of Helsinki（赫尔辛基大学）；Aalto University（阿尔托大学）
We propose a numerical accountant for evaluating the tight $(\varepsilon,δ)$-privacy loss for algorithms with discrete one dimensional output. The method is based on the privacy loss distribution formalism and it uses the recently introduced fast Fourier transform based accounting technique. We carry out an error analysis of the method in terms of moment bounds of the privacy loss distribution which leads to rigorous lower and upper bounds for the true $(\varepsilon,δ)$-values. As an application, we present a novel approach to accurate privacy accounting of the subsampled Gaussian mechanism. T…
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）；Aalto University（阿尔托大学）
Differentially private (DP) machine learning has recently become popular. The privacy loss of DP algorithms is commonly reported using $(\varepsilon,δ)$-DP. In this paper, we propose a numerical accountant for evaluating the privacy loss for algorithms with continuous one dimensional output. This accountant can be applied to the subsampled multidimensional Gaussian mechanism which underlies the popular DP stochastic gradient descent. The proposed method is based on a numerical approximation of an integral formula which gives the exact $(\varepsilon,δ)$-values. The approximation is carried out …
Fast Fourier Transform-Based Spectral and Temporal Gradient Filtering for Differential Privacy
Electronics and Telecommunications Research Institute (ETRI)（电子电信研究所）；University of Southern California（南加州大学）；KAIST（韩国科学技术院）；Hanwha Life Insurance（翰威特生命保险）；OpenNN Lab, MODULABS（OpenNN实验室，MODULABS）
New Jersey Institute of Technology（新泽西理工学院）；Kent State University（肯特州立大学）；University of Oregon（俄勒冈大学）；University of Arkansas（阿肯色大学）；University of Florida（佛罗里达大学）
In this paper, we propose a novel Heterogeneous Gaussian Mechanism (HGM) to preserve differential privacy in deep neural networks, with provable robustness against adversarial examples. We first relax the constraint of the privacy budget in the traditional Gaussian Mechanism from (0, 1] to (0, \infty), with a new bound of the noise scale to preserve differential privacy. The noise in our mechanism can be arbitrarily redistributed, offering a distinctive ability to address the trade-off between model utility and privacy loss. To derive provable robustness, our HGM is applied to inject Gaussian …
Stanford University（斯坦福大学）；Microsoft Research（微软研究院）；U.S. Bureau of Economic Analysis（美国经济分析局）
Estimating heterogeneous treatment effects in domains such as healthcare or social science often involves sensitive data where protecting privacy is important. We introduce a general meta-algorithm for estimating conditional average treatment effects (CATE) with differential privacy (DP) guarantees. Our meta-algorithm can work with simple, single-stage CATE estimators such as S-learner and more complex multi-stage estimators such as DR and R-learner. We perform a tight privacy analysis by taking advantage of sample splitting in our meta-algorithm and the parallel composition property of differ…
Federated learning (FL) takes a first step towards privacy-preserving machine learning by training models while keeping client data local. Models trained using FL may still leak private client information through model updates during training. Differential privacy (DP) may be employed on model updates to provide privacy guarantees within FL, typically at the cost of degraded performance of the final trained model. Both non-private FL and DP-FL can be solved using variants of the federated averaging (FedAvg) algorithm. In this work, we consider a heterogeneous DP setup where clients require var…
Many application scenarios call for training a machine learning model among multiple participants. Federated learning (FL) was proposed to enable joint training of a deep learning model using the local data in each party without revealing the data to others. Among various types of FL methods, vertical FL is a category to handle data sources with the same ID space and different feature spaces. However, existing vertical FL methods suffer from limitations such as restrictive neural network structure, slow training speed, and often lack the ability to take advantage of data with unmatched IDs. In…
PDSL: Privacy-Preserved Decentralized Stochastic Learning with Heterogeneous Data Distribution
School of Computer Science and Technology, Shandong University（山东大学计算机科学与技术学院）；Shandong Computer Science Center (National Supercomputer Center in Jinan)（山东省计算中心（国家超级计算济南中心））；Qilu University of Technology (Shandong Academy of Sciences)（齐鲁工业大学（山东省科学院））；Shandong Fundamental Research Center for Computer Science（山东省计算机科学基础研究中心）
University of Pittsburgh（匹兹堡大学）；University of Massachusetts Amherst（马萨诸塞大学阿默斯特分校）
Internet of Things (IoT) devices are becoming increasingly popular and are influencing many application domains such as healthcare and transportation. These devices are used for real-world applications such as sensor monitoring, real-time control. In this work, we look at differentially private (DP) neural network (NN) based network intrusion detection systems (NIDS) to detect intrusion attacks on networks of such IoT devices. Existing NN training solutions in this domain either ignore privacy considerations or assume that the privacy requirements are homogeneous across all users. We show that…
University of Potsdam（波茨坦大学）；Hasso Plattner Institute for Digital Engineering gGmbH（哈索·普拉特纳数字工程研究院）；Philips Research（飞利浦研究院）
Privacy regulations and the physical distribution of heterogeneous data are often primary concerns for the development of deep learning models in a medical context. This paper evaluates the feasibility of differentially private federated learning for chest X-ray classification as a defense against data privacy attacks. To the best of our knowledge, we are the first to directly compare the impact of differentially private training on two different neural network architectures, DenseNet121 and ResNet50. Extending the federated learning environments previously analyzed in terms of privacy, we sim…
Federated Learning is a distributed machine-learning environment that allows clients to learn collaboratively without sharing private data. This is accomplished by exchanging parameters. However, the differences in data distributions and computing resources among clients make related studies difficult. To address these heterogeneous problems, we propose a novel Federated Learning method. Our method utilizes a pre-trained model as the backbone of the local model, with fully connected layers comprising the head. The backbone extracts features for the head, and the embedding vector of classes is …
LAPA-based Dynamic Privacy Optimization for Wireless Federated Learning in Heterogeneous Environments
College of Electronics and Information Engineering, Tongji University（同济大学电子与信息工程学院）；Commonwealth Science and Industrial Research Organization (CSIRO)（共同科学与工业研究组织）；School of Electrical and Information Engineering Faculty of Engineering, The University of Sydney（悉尼大学电气与信息工程学院）
The Power of Bias: Optimizing Client Selection in Federated Learning with Heterogeneous Differential Privacy
College of Computer Science and Software Engineering, Shenzhen University（深圳大学计算机与软件学院）；Guangdong Laboratory of Artificial Intelligence and Digital Economy (SZ), Shenzhen University（深圳大学广东省人工智能与数字经济实验室（SZ））；School of Computing, Faculty of Science and Engineering, Macquarie University（麦考瑞大学科学与工程学院计算学院）；Institute for Network Sciences and Cyberspace, Tsinghua University（清华大学网络科学与网络空间研究院）；School of Computing Science, Simon Fraser University（西蒙菲莎大学计算科学学院）
University of Massachusetts, Amherst（马萨诸塞大学阿默斯特分校）；Google Research NYC（谷歌研究院纽约分部）
Differential privacy is widely adopted to provide provable privacy guarantees in data analysis. We consider the problem of combining public and private data (and, more generally, data with heterogeneous privacy needs) for estimating aggregate statistics. We introduce a mixed estimator of the mean optimized to minimize the variance. We argue that our mechanism is preferable to techniques that preserve the privacy of individuals by subsampling data proportionally to the privacy needs of users. Similarly, we present a mixed median estimator based on the exponential mechanism. We compare our mecha…
Ecole Polytechnique（巴黎综合理工学院）；Institut Polytechnique de Paris（巴黎理工学院）；Univ. Lille（里尔大学）；Inria（法国国家信息与自动化研究所）；CNRS（法国国家科学研究中心）；Centrale Lille（里尔中央理工学院）
Federated Learning (FL) is a paradigm for large-scale distributed learning which faces two key challenges: (i) efficient training from highly heterogeneous user data, and (ii) protecting the privacy of participating users. In this work, we propose a novel FL approach (DP-SCAFFOLD) to tackle these two challenges together by incorporating Differential Privacy (DP) constraints into the popular SCAFFOLD algorithm. We focus on the challenging setting where users communicate with a "honest-but-curious" server without any trusted intermediary, which requires to ensure privacy not only towards a third…
Stabilizing Private LASSO under Heterogeneous Covariates via Anisotropic Objective Perturbation
Department of Information Science Ochanomizu University Bunkyo-ku, Tokyo, Japan（信息科学系, 陈仓区, 东京, 日本, 东方大学）；RIKEN center for AIP Chuo-ku, Tokyo, Japan（理化学研究所AIP研究中心, 东京都, 东京, 日本）
Recent attacks on federated learning demonstrate that keeping the training data on clients' devices does not provide sufficient privacy, as the model parameters shared by clients can leak information about their training data. A 'secure aggregation' protocol enables the server to aggregate clients' models in a privacy-preserving manner. However, existing secure aggregation protocols incur high computation/communication costs, especially when the number of model parameters is larger than the number of clients participating in an iteration -- a typical scenario in federated learning. In this pap…
Electronic Health Records (EHRs) are commonly used by the machine learning community for research on problems specifically related to health care and medicine. EHRs have the advantages that they can be easily distributed and contain many features useful for e.g. classification problems. What makes EHR data sets different from typical machine learning data sets is that they are often very sparse, due to their high dimensionality, and often contain heterogeneous (mixed) data types. Furthermore, the data sets deal with sensitive information, which limits the distribution of any models learned usi…
Federated learning (FL) provides a privacy-preserving solution for distributed machine learning tasks. One challenging problem that severely damages the performance of FL models is the co-occurrence of data heterogeneity and long-tail distribution, which frequently appears in real FL applications. In this paper, we reveal an intriguing fact that the biased classifier is the primary factor leading to the poor performance of the global model. Motivated by the above finding, we propose a novel and privacy-preserving FL method for heterogeneous and long-tailed data via Classifier Re-training with …
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）
Federated Learning with Gramian Angular Fields for Privacy-Preserving ECG Classification on Heterogeneous IoT Devices
Laboratoire LITAN（LITAN实验室）；École supérieure en Sciences et Technologies de l’Informatique et du Numérique（信息与数字技术高级学院）；College of Engineering and IT（工程与信息技术学院）；University of Dubai（迪拜大学）；Department of Computer Science（计算机科学系）；University of Sharjah（沙迦大学）
Southern University of Science and Technology（南方科技大学）
Federated learning (FL) has been proposed to protect data privacy and virtually assemble the isolated data silos by cooperatively training models among organizations without breaching privacy and security. However, FL faces heterogeneity from various aspects, including data space, statistical, and system heterogeneity. For example, collaborative organizations without conflict of interest often come from different areas and have heterogeneous data from different feature spaces. Participants may also want to train heterogeneous personalized local models due to non-IID and imbalanced data distrib…
Towards Personalized Differentially Private Learning for Decentralized Local Graphs
School of Computer Science, Beijing University of Posts and Telecommunications（北京邮电大学计算机学院）；State Key Laboratory of Networking and Switching Technology, Beijing University of Posts and Telecommunications（北京邮电大学网络与交换技术国家重点实验室）；School of Cyber Science and Technology, Shandong University（山东大学网络空间安全学院）；School of Cyberspace Security, Beijing University of Posts and Telecommunications（北京邮电大学网络空间安全学院）；Department of Computer Science, University of Illinois at Chicago（伊利诺伊大学芝加哥分校计算机科学系）
Telefonica Research（西班牙电信研究院）；Cornell Tech（康奈尔理工学院）；Vassar College（瓦萨学院）；Pomona College（波莫纳学院）；Imperial College London（伦敦帝国学院）
In this paper we present PoliFL, a decentralized, edge-based framework that supports heterogeneous privacy policies for federated learning. We evaluate our system on three use cases that train models with sensitive user data collected by mobile phones - predictive text, image classification, and notification engagement prediction - on a Raspberry Pi edge device. We find that PoliFL is able to perform accurate model training and inference within reasonable resource and time budgets while also enforcing heterogeneous privacy policies.
