Efficient and Private Scoring of Decision Trees, Support Vector Machines and Logistic Regression Models Based on Pre-Computation

Cock, Martine De; Dowsley, Rafael; Horst, Caleb; Katti, R.; Nascimento, Anderson C. A.; Poon, Wing-Sea; Truex, Stacey

doi:10.1109/tdsc.2017.2679189

Cited by 117 publications

(110 citation statements)

References 39 publications

Supporting

Mentioning

108

Contrasting

Order By: Relevance

“…Non-application specific protocols were designed just lately. Bost et al [17] introduced privacypreserving protocols for hyperplane-based, Naive Bayes and DT classifiers, Wu et al [18] for DTs and RFs, David et al [19] for hyperplane-based and Naive Bayes classifiers, and De Cock et al [20] for DTs and hyperplane-based classifiers. De Hoogh et al [14] had also previously presented a protocol for privacy-preserving scoring of DTs with categorical attributes.…”

Section: Related Workmentioning

confidence: 99%

“…De Hoogh et al [14] had also previously presented a protocol for privacy-preserving scoring of DTs with categorical attributes. The protocol for privacy-preserving scoring of DTs of De Cock et al [20] cannot be directly used as a building block to obtain random forests and boosted decision trees. We present in Section III a modified protocol for scoring decision trees that does the job.…”

Section: Related Workmentioning

confidence: 99%

“…An honest-but-curious adversary follows the instructions of the protocol, but tries to gather additional information. We use as a building block an adaptation of the protocol for privacy-preserving scoring of DTs of De Cock et al [20], which we recall in Section III-C, after presenting preliminaries about the security model in Section III-B.…”

Section: A Problem Descriptionmentioning

confidence: 99%

“…The commodity-based model allows the realization of non-trivial functionality in the UC framework and has already been used to get very efficient secure computation protocols for tasks such as computing inner-products [29], [30] and other linear algebra operations [31], string equality [30], set intersection [30], oblivious polynomial evaluation [32] and verifiable secret sharing [33]. It was used in protocols for PPML [15], [19], [20]. In practice, this correlated randomness can be distributed by: (1) a single trusted server, (2) many not completely trusted servers (only a majority of honest servers is necessary [28]), or (3) pre-computed by the parties in an offline phase using an SMC protocol to emulate the trusted initializer (in this case the advantage is in offloading the heavy computation to be run at any idle time).…”

Section: B Cryptographic Preliminaries and Building Blocksmentioning

confidence: 99%

See 3 more Smart Citations

Privacy-Preserving Scoring of Tree Ensembles: A Novel Framework for AI in Healthcare

Fritchman

Saminathan

Dowsley

et al. 2018

2018 IEEE International Conference on Big Data (Big Data)

Self Cite

View full text Add to dashboard Cite

Machine Learning (ML) techniques now impact a wide variety of domains. Highly regulated industries such as healthcare and finance have stringent compliance and data governance policies around data sharing. Advances in secure multiparty computation (SMC) for privacy-preserving machine learning (PPML) can help transform these regulated industries by allowing ML computations over encrypted data with personally identifiable information (PII). Yet very little of SMC-based PPML has been put into practice so far. In this paper we present the very first framework for privacypreserving classification of tree ensembles with application in healthcare. We first describe the underlying cryptographic protocols that enable a healthcare organization to send encrypted data securely to a ML scoring service and obtain encrypted class labels without the scoring service actually seeing that input in the clear. We then describe the deployment challenges we solved to integrate these protocols in a cloud based scalable risk-prediction platform with multiple ML models for healthcare AI. Included are system internals, and evaluations of our deployment for supporting physicians to drive better clinical outcomes in an accurate, scalable, and provably secure manner. To the best of our knowledge, this is the first such applied framework with SMC-based privacypreserving machine learning for healthcare.

show abstract

Section: Related Workmentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

Section: A Problem Descriptionmentioning

confidence: 99%

Section: B Cryptographic Preliminaries and Building Blocksmentioning

confidence: 99%

See 2 more Smart Citations

Privacy-Preserving Scoring of Tree Ensembles: A Novel Framework for AI in Healthcare

Fritchman

Saminathan

Dowsley

et al. 2018

2018 IEEE International Conference on Big Data (Big Data)

Self Cite

View full text Add to dashboard Cite

show abstract

“…The calculation in the training and the test phase is very complicated when SOM as the classifier which requires multiple vector multiplications, or more complex divition. Secure Multi-party Computation (SMC) [23], [24] may enable secure cross-domain anomaly detection (e.g., secure addition protocol, secure multiplication protocol and secure compare protocol). However, these protocols require a large amount of interaction from the participants and calculations on ciphertext, which undoubtedly consumes many of the controller's bandwidth.…”

Section: Introductionmentioning

confidence: 99%

Privacy-Preserving DDoS Attack Detection Using Cross-Domain Traffic in Software Defined Networks

Zhu

Tang

Shen

et al. 2018

IEEE J. Select. Areas Commun.

103

View full text Add to dashboard Cite

Existing Distributed Denial-of-Service (DDoS) attacks detections in software defined networks (SDNs) typically only carry out detection in a single domain. In reality, abnormal traffic usually affects multiple network domains. Thus, the cross-domain attacks detection has been proposed to improve the detection performance. However when participating in the detection each SDNs domain needs to provide a large number of real traffic data where private information may be leaked out. Existing multiparty privacy protection schemes often achieve privacy guarantees by sacrificing accuracy or increasing the time cost. It is a challenging task to have both high accuracy and reasonable time consumption.In this paper, we propose Predis, a privacy-preserving cross-domain attacks detection scheme for SDNs. Predis combines perturbation encryption and data encryption to protect privacy, and uses a computationally simple and efficient algorithm k-Nearest Neighbor (kNN) as its detection algorithm. We also improve the kNN to achieve better efficiency. Through theoretical analysis and extensive simulations, we demonstrate that Predis is capable to achieve efficient and accurate attacks detection, while keeping sensitive information of each domain secure.

show abstract

Secure decision tree twin support vector machine training and classification process for encrypted IoT data via blockchain platform

Dey

Chaulya

Kumar

2021

Concurrency and Computation

View full text Add to dashboard Cite

A secure decision tree twin support vector machine (DT-TSVM) multi-classification algorithm has been proposed in this paper for improving the reliability and security of the collected IoT data from multiple data providers. The multiclass secure DT-TSVM algorithm has been employed to train a machine learning model using the encrypted training dataset. The training dataset is collected via a blockchain platform.A blockchain method has been adopted to construct a secure and reliable distributed platform among dataset providers. The Paillier homomorphic cryptosystem has been applied for encrypting the IoT dataset. Then, the dataset has been recorded on the distributed ledger. The secure DT-TSVM algorithm's-based train model effectiveness has been compared with the other two available algorithms, namely the multiclass binary support vector machine (MBSVM) and one-to-one SVM algorithms. The experiment results showed that the privacy-preserving multiclass secure DT-TSVM-based model did not reduce the accuracy, but it increased the average precision and recall by 0.53% and 0.44% than MBSVM and 0.82% and 0.71% than one-to-one SVM, respectively. Further, the time consumption of data providers and data analysts did not change significantly with the increase of number of data provider.

show abstract

Efficient and Private Scoring of Decision Trees, Support Vector Machines and Logistic Regression Models Based on Pre-Computation

Cited by 117 publications

References 39 publications

Privacy-Preserving Scoring of Tree Ensembles: A Novel Framework for AI in Healthcare

Privacy-Preserving Scoring of Tree Ensembles: A Novel Framework for AI in Healthcare

Privacy-Preserving DDoS Attack Detection Using Cross-Domain Traffic in Software Defined Networks

Secure decision tree twin support vector machine training and classification process for encrypted IoT data via blockchain platform

Contact Info

Product

Resources

About