In this paper, we present a secure logistic regression training protocol and its implementation, with a new subprotocol to securely compute the activation function. To the best of our knowledge, we present the fastest existing secure Multi-Party Computation implementation for training logistic regression models on high dimensional genome data distributed across a local area network.
Sabanci University（萨班哲大学）；North Carolina State University（北卡罗来纳州立大学）
Preserving the privacy and security of big data in the context of cloud computing, while maintaining a certain level of efficiency of its processing remains to be a subject, open for improvement. One of the most popular applications epitomizing said concerns is found to be useful in genome analysis. This work proposes a secure multi-label tumor classification method using homomorphic encryption, whereby two different machine learning algorithms, SVM and XGBoost, are used to classify the encrypted genome data of different tumor types.
Privacy is of the utmost importance in genomic matching. Therefore a number of privacy-preserving protocols have been presented using secure computation. Nevertheless, none of these protocols prevents inferences from the result. Goodrich has shown that this resulting information is sufficient for an effective attack on genome databases. In this paper we present an approach that can detect and mitigate such an attack on encrypted messages while still preserving the privacy of both parties. Note that randomization, e.g.~using differential privacy, will almost certainly destroy the utility of the…
Over the past several years, DNA sequencing has emerged as one of the driving forces in life-sciences, paving the way for affordable and accurate whole genome sequencing. As genomes represent the entirety of an organism's hereditary information, the availability of complete human genomes prompts a wide range of revolutionary applications. The hope for improving modern healthcare and better understanding the human genome propels many interesting and challenging research frontiers. Unfortunately, however, the proliferation of human genomes amplifies worrisome privacy concerns, since a genome rep…
Rapid advances in human genomics are enabling researchers to gain a better understanding of the role of the genome in our health and well-being, stimulating hope for more effective and cost efficient healthcare. However, this also prompts a number of security and privacy concerns stemming from the distinctive characteristics of genomic data. To address them, a new research community has emerged and produced a large number of publications and initiatives. In this paper, we rely on a structured methodology to contextualize and provide a critical analysis of the current knowledge on privacy-enhan…
Traditional statistical methods for confidentiality protection of statistical databases do not scale well to deal with GWAS (genome-wide association studies) databases especially in terms of guarantees regarding protection from linkage to external information. The more recent concept of differential privacy, introduced by the cryptographic community, is an approach which provides a rigorous definition of privacy with meaningful privacy guarantees in the presence of arbitrary external information, although the guarantees come at a serious price in terms of data utility. Building on such notions…
Logistics Information System (LIS) is an interactive system that provides information for logistics managers to monitor and track logistics business. In recent years, with the rise of online shopping, LIS is becoming increasingly important. However, since the lack of effective protection of personal information, privacy protection issue has become the most problem concerned by users. Some data breach events in LIS released users' personal information, including address, phone number, transaction details, etc. In this paper, to protect users' privacy in LIS, a privacy-preserving LIS with tracea…
Genome sequencing technology has advanced at a rapid pace and it is now possible to generate highly-detailed genotypes inexpensively. The collection and analysis of such data has the potential to support various applications, including personalized medical services. While the benefits of the genomics revolution are trumpeted by the biomedical community, the increased availability of such data has major implications for personal privacy; notably because the genome has certain essential features, which include (but are not limited to) (i) an association with traits and certain diseases, (ii) ide…
Genome-wide Association Studies (GWASes) identify genomic variations that are statistically associated with a trait, such as a disease, in a group of individuals. Unfortunately, careless sharing of GWAS statistics might give rise to privacy attacks. Several works attempted to reconcile secure processing with privacy-preserving releases of GWASes. However, we highlight that these approaches remain vulnerable if GWASes utilize overlapping sets of individuals and genomic variations. In such conditions, we show that even when relying on state-of-the-art techniques for protecting releases, an adver…
Vanderbilt University（范德堡大学）；University of Virginia（弗吉尼亚大学）
Safeguarding privacy in machine learning is highly desirable, especially in collaborative studies across many organizations. Privacy-preserving distributed machine learning (based on cryptography) is popular to solve the problem. However, existing cryptographic protocols still incur excess computational overhead. Here, we make a novel observation that this is partially due to naive adoption of mainstream numerical optimization (e.g., Newton method) and failing to tailor for secure computing. This work presents a contrasting perspective: customizing numerical optimization specifically for secur…
We consider vertical logistic regression (VLR) trained with mini-batch gradient descent -- a setting which has attracted growing interest among industries and proven to be useful in a wide range of applications including finance and medical research. We provide a comprehensive and rigorous privacy analysis of VLR in a class of open-source Federated Learning frameworks, where the protocols might differ between one another, yet a procedure of obtaining local gradients is implicitly shared. We first consider the honest-but-curious threat model, in which the detailed implementation of protocol is …
We study the privacy risks that are associated with training a neural network's weights with self-supervised learning algorithms. Through empirical evidence, we show that the fine-tuning stage, in which the network weights are updated with an informative and often private dataset, is vulnerable to privacy attacks. To address the vulnerabilities, we design a post-training privacy-protection algorithm that adds noise to the fine-tuned weights and propose a novel differential privacy mechanism that samples noise from the logistic distribution. Compared to the two conventional additive noise mecha…
Genome-wide association studies (GWAS) identify correlations between the genetic variants and an observable characteristic such as a disease. Previous works presented privacy-preserving distributed algorithms for a federation of genome data holders that spans multiple institutional and legislative domains to securely compute GWAS results. However, these algorithms have limited applicability, since they still require a centralized instance to decide whether GWAS results can be safely disclosed, which is in violation to privacy regulations, such as GDPR. In this work, we introduce GenDPR, a dist…
Internet of Things devices are expanding rapidly and generating huge amount of data. There is an increasing need to explore data collected from these devices. Collaborative learning provides a strategic solution for the Internet of Things settings but also raises public concern over data privacy. In recent years, large amount of privacy preserving techniques have been developed based on secure multi-party computation and differential privacy. A major challenge of collaborative learning is to balance disclosure risk and data utility while maintaining high computation efficiency. In this paper, …
In recent years, Whole Genome Sequencing (WGS) evolved from a futuristic-sounding research project to an increasingly affordable technology for determining complete genome sequences of complex organisms, including humans. This prompts a wide range of revolutionary applications, as WGS promises to improve modern healthcare and provide a better understanding of the human genome -- in particular, its relation to diseases and response to treatments. However, this progress raises worrisome privacy and ethical issues, since, besides uniquely identifying its owner, the genome contains a treasure trov…
In recent years, machine learning techniques are widely used in numerous applications, such as weather forecast, financial data analysis, spam filtering, and medical prediction. In the meantime, massive data generated from multiple sources further improve the performance of machine learning tools. However, data sharing from multiple sources brings privacy issues for those sources since sensitive information may be leaked in this process. In this paper, we propose a framework enabling multiple parties to collaboratively and accurately train a learning model over distributed datasets while guara…
Providing provenance in scientific workflows is essential for reproducibility and auditability purposes. Workflow systems model and record provenance describing the steps performed to obtain the final results of a computation. In this work, we propose a framework that verifies the correctness of the statistical test results that are conducted by a researcher while protecting individuals' privacy in the researcher's dataset. The researcher publishes the workflow of the conducted study, its output, and associated metadata. They keep the research dataset private while providing, as part of the me…
Planning is one of the main approaches used to improve agents' working efficiency by making plans beforehand. However, during planning, agents face the risk of having their private information leaked. This paper proposes a novel strong privacy-preserving planning approach for logistic-like problems. This approach outperforms existing approaches by addressing two challenges: 1) simultaneously achieving strong privacy, completeness and efficiency, and 2) addressing communication constraints. These two challenges are prevalent in many real-world applications including logistics in military enviro…
Recent advances in DNA sequencing technologies have put ubiquitous availability of fully sequenced human genomes within reach. It is no longer hard to imagine the day when everyone will have the means to obtain and store one's own DNA sequence. Widespread and affordable availability of fully sequenced genomes immediately opens up important opportunities in a number of health-related fields. In particular, common genomic applications and tests performed in vitro today will soon be conducted computationally, using digitized genomes. New applications will be developed as genome-enabled medicine b…
Beijing Key Laboratory of Information Service Engineering, Beijing Union University（北京联合大学信息服务业工程北京市重点实验室）；Vanderbilt University（范德堡大学）
As one of the most popular statistical and machine learning models, logistic regression with regularization has found wide adoption in biomedicine, social sciences, information technology, and so on. These domains often involve data of human subjects that are contingent upon strict privacy regulations. Increasing concerns over data privacy make it more and more difficult to coordinate and conduct large-scale collaborative studies, which typically rely on cross-institution data sharing and joint analysis. Our work here focuses on safeguarding regularized logistic regression, a widely-used machi…
The genome is a unique identifier for human individuals. The genome also contains highly sensitive information, creating a high potential for misuse of genomic data (for example, genetic discrimination). In this paper, I investigated how genomic privacy can be measured in scenarios where an adversary aims to infer a person's genomic markers by constructing probability distributions on the values of genetic variations. I measured the strength of privacy metrics by requiring that metrics are monotonic with increasing adversary strength and uncovered serious problems with several existing metrics…
Northwest University（西北大学）；Macau University of Science and Technology（澳门科技大学）
In this paper, we present a differential privacy version of convex and nonconvex sparse classification approach. Based on alternating direction method of multiplier (ADMM) algorithm, we transform the solving of sparse problem into the multistep iteration process. Then we add exponential noise to stable steps to achieve privacy protection. By the property of the post-processing holding of differential privacy, the proposed approach satisfies the $ε-$differential privacy even when the original problem is unstable. Furthermore, we present the theoretical privacy bound of the differential privacy …
Sharing genome data in a privacy-preserving way stands as a major bottleneck in front of the scientific progress promised by the big data era in genomics. A community-driven protocol named genomic data-sharing beacon protocol has been widely adopted for sharing genomic data. The system aims to provide a secure, easy to implement, and standardized interface for data sharing by only allowing yes/no queries on the presence of specific alleles in the dataset. However, beacon protocol was recently shown to be vulnerable against membership inference attacks. In this paper, we show that privacy threa…
Since the 90s, keyword-based search engines have been helping people locate relevant web content via a simple query, so have the recent full-text-based search engines mainly used for plagiarism detection following an article upload. However, these "free" or paid services operate by storing users' search queries and preferences for personal profiling and targeted ads delivery, while user-uploaded articles can further profit the service providers as part of their expanding databases. In short, search engine privacy has not been an option for web exploration in the past decades. Here we demonstra…
Federated learning is emerging as a machine learning technique that trains a model across multiple decentralized parties. It is renowned for preserving privacy as the data never leaves the computational devices, and recent approaches further enhance its privacy by hiding messages transferred in encryption. However, we found that despite the efforts, federated learning remains privacy-threatening, due to its interactive nature across different parties. In this paper, we analyze the privacy threats in industrial-level federated learning frameworks with secure computation, and reveal such threats…
Consider two parties who want to compare their strings, e.g., genomes, but do not want to reveal them to each other. We present a system for privacy-preserving matching of strings, which differs from existing systems by providing a deterministic approximation instead of an exact distance. It is efficient (linear complexity), non-interactive and does not involve a third party which makes it particularly suitable for cloud computing. We extend our protocol, such that it mitigates iterated differential attacks proposed by Goodrich. Further an implementation of the system is evaluated and compared…
Aalto University（阿尔托大学）；University of Helsinki（赫尔辛基大学）；University of Manchester（曼彻斯特大学）
Generalized linear models (GLMs) such as logistic regression are among the most widely used arms in data analyst's repertoire and often used on sensitive datasets. A large body of prior works that investigate GLMs under differential privacy (DP) constraints provide only private point estimates of the regression coefficients, and are not able to quantify parameter uncertainty. In this work, with logistic and Poisson regression as running examples, we introduce a generic noise-aware DP Bayesian inference method for a GLM at hand, given a noisy sum of summary statistics. Quantifying uncertainty a…
Institute for Development and Research in Banking Technology（银行技术发展与研究所）；University of Hyderabad（海得拉巴大学）
The Machine Learning and Deep Learning Models require a lot of data for the training process, and in some scenarios, there might be some sensitive data, such as customer information involved, which the organizations might be hesitant to outsource for model building. Some of the privacy-preserving techniques such as Differential Privacy, Homomorphic Encryption, and Secure Multi-Party Computation can be integrated with different Machine Learning and Deep Learning algorithms to provide security to the data as well as the model. In this paper, we propose a Chaotic Extreme Learning Machine and its …
Data integration and sharing maximally enhance the potential for novel and meaningful discoveries. However, it is a non-trivial task as integrating data from multiple sources can put sensitive information of study participants at risk. To address the privacy concern, we present a distributed Bayesian learning approach via Preconditioned Stochastic Gradient Langevin Dynamics with RMSprop, which combines differential privacy and homomorphic encryption in a harmonious manner while protecting private information. We applied the proposed secure and privacy-preserving distributed Bayesian learning a…
Recent studies demonstrate that effective healthcare can benefit from using the human genomic information. For instance, analysis of tumor genomes has revealed 140 genes whose mutations contribute to cancer. As a result, many institutions are using statistical analysis of genomic data, which are mostly based on genome-wide association studies (GWAS). GWAS analyze genome sequence variations in order to identify genetic risk factors for diseases. These studies often require pooling data from different sources together in order to unravel statistical patterns or relationships between genetic vari…
Email is a private medium of communication, and the inherent privacy constraints form a major obstacle in developing effective spam filtering methods which require access to a large amount of email data belonging to multiple users. To mitigate this problem, we envision a privacy preserving spam filtering system, where the server is able to train and evaluate a logistic regression based spam classifier on the combined email data of all users without being able to observe any emails using primitives such as homomorphic encryption and randomization. We analyze the protocols for correctness and se…
Booz Allen Hamilton（博思艾伦汉密尔顿公司）；University of Maryland, Baltimore County（马里兰大学巴尔的摩县分校）；Air Force Research Laboratory（美国空军研究实验室）
We present a framework to statistically audit the privacy guarantee conferred by a differentially private machine learner in practice. While previous works have taken steps toward evaluating privacy loss through poisoning attacks or membership inference, they have been tailored to specific models or have demonstrated low statistical power. Our work develops a general methodology to empirically evaluate the privacy of differentially private machine learning implementations, combining improved privacy search and verification methods with a toolkit of influence-based poisoning attacks. We demonst…
Federated Learning (FL) enables a large number of users to jointly learn a shared machine learning (ML) model, coordinated by a centralized server, where the data is distributed across multiple devices. This approach enables the server or users to train and learn an ML model using gradient descent, while keeping all the training data on users' devices. We consider training an ML model over a mobile network where user dropout is a common phenomenon. Although federated learning was aimed at reducing data privacy risks, the ML model privacy has not received much attention. In this work, we presen…
The foreseen growing role of outsourced machine learning services is raising concerns about the privacy of user data. Several technical solutions are being proposed to address the issue. Hardware security modules in cloud data centres appear limited to enterprise customers due to their complexity, while general multi-party computation techniques require a large number of message exchanges. This paper proposes a variety of protocols for privacy-preserving regression and classification that (i) only require additively homomorphic encryption algorithms, (ii) limit interactions to a mere request a…
Indian Institute of Engineering Science and Technology, Shibpur（希布尔印度工程科学与技术学院）；University of New South Wales（新南威尔士大学）
Recently collaborative learning is widely applied to model sensitive data generated in Industrial IoT (IIoT). It enables a large number of devices to collectively train a global model by collaborating with a server while keeping the datasets on their respective premises. However, existing approaches are limited by high overheads and may also suffer from falsified aggregated results returned by a malicious server. Hence, we propose a Scalable, Privacy-preserving and veRIfiable collaboraTive lEarning (SPRITE) algorithm to train linear and logistic regression models for IIoT. We aim to reduce bur…
Preserving the privacy of individual databases when carrying out statistical calculations has a long history in statistics and had been the focus of much recent attention in machine learning In this paper, we present a protocol for computing logistic regression when the data are held by separate parties without actually combining information sources by exploiting results from the literature on multi-party secure computation. We provide only the final result of the calculation compared with other methods that share intermediate values and thus present an opportunity for compromise of values in …
Leveraging transfer learning has recently been shown to be an effective strategy for training large models with Differential Privacy (DP). Moreover, somewhat surprisingly, recent works have found that privately training just the last layer of a pre-trained model provides the best utility with DP. While past studies largely rely on algorithms like DP-SGD for training large models, in the specific case of privately learning from features, we observe that computational burden is low enough to allow for more sophisticated optimization schemes, including second-order methods. To that end, we system…
Training Differentially Private Models with Secure Multiparty Computation
School of Engineering and Technology, University of Washington Tacoma（华盛顿大学塔科马分校工程与技术学院）；University of Brasilia（巴西利亚大学）；Monash University（莫纳什大学）；Ghent University（根特大学）；Mila – Quebec AI Institute（米拉-魁北克人工智能研究所）
Suppose Alice holds a DNA sequence and Bob owns a database of DNA sequences. They want to determine whether there is a match for the Alice's input in the Bob's database for any purpose such as diagnosis of Alice's disease. However, Alice does not want to reveal her DNA pattern to Bob, since it would enable him to learn private information about her. For the similar reasons, Bob does not want to reveal any information about his database to Alice. This problem has attracted attention from bioinformatics community in order to protect privacy of users and several solutions have been proposed. Effi…
University of Southern California（南加州大学）；University of California, Riverside（加州大学河滨分校）
How to train a machine learning model while keeping the data private and secure? We present CodedPrivateML, a fast and scalable approach to this critical problem. CodedPrivateML keeps both the data and the model information-theoretically private, while allowing efficient parallelization of training across distributed workers. We characterize CodedPrivateML's privacy threshold and prove its convergence for logistic (and linear) regression. Furthermore, via extensive experiments on Amazon EC2, we demonstrate that CodedPrivateML provides significant speedup over cryptographic approaches based on …
Secure multi-party computation enables multiple mutually distrusting parties to perform computations on data without revealing the data itself, and has become one of the core technologies behind privacy-preserving machine learning. In this work, we present several improved privacy-preserving protocols for both linear and non-linear layers in machine learning. For linear layers, we present an extended beaver triple protocol for bilinear maps that significantly reduces communication of convolution layer. For non-linear layers, we introduce novel protocols for computing the sigmoid and softmax fu…
We introduce PrivPy, a practical privacy-preserving collaborative computation framework, especially optimized for machine learning tasks. PrivPy provides an easy-to-use and highly compatible Python programming front-end which supports high-level array operations and different secure computation engines to allow for security assumptions and performance trade-offs. With PrivPy, programmers can write modern machine learning algorithms conveniently and efficiently in Python. We also design and implement a new efficient computation engine, with which people can use competing cloud providers to effi…
In the recent years, pixel-based perceptual algorithms have been successfully applied for privacy-preserving deep learning (DL) based applications. However, their security has been broken in subsequent works by demonstrating a chosen-plaintext attack. In this paper, we propose an efficient pixel-based perceptual encryption method. The method provides a necessary level of security while preserving the intrinsic properties of the original image. Thereby, can enable deep learning (DL) applications in the encryption domain. The method is substitution based where pixel values are XORed with a seque…
School of Engineering and Technology, University of Washington Tacoma（华盛顿大学塔科马分校工程与技术学院）；Faculty of Information Technology, Monash University（莫纳什大学信息技术学院）；Ghent University（根特大学）
Classification of personal text messages has many useful applications in surveillance, e-commerce, and mental health care, to name a few. Giving applications access to personal texts can easily lead to (un)intentional privacy violations. We propose the first privacy-preserving solution for text classification that is provably secure. Our method, which is based on Secure Multiparty Computation (SMC), encompasses both feature extraction from texts, and subsequent classification with logistic regression and tree ensembles. We prove that when using our secure text classification method, the applic…
