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

Fritchman, Kyle; Saminathan, Keerthanaa; Dowsley, Rafael; Hughes, Tyler W.; Cock, Martine De; Nascimento, Anderson C. A.; Teredesai, Ankur

doi:10.1109/bigdata.2018.8622627

Cited by 36 publications

(16 citation statements)

References 28 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Interesting directions for future work are direct adaptations of grid-search by training multiple models with multiple different hyperparameters jointly amongst the parties. Then, in conjunction with protocols for privacy-preserving inference [8,22], we could perform a secure comparison of all of the results, obliviously select the most accurate model with the best hyperparameters, and use that to classify new, unseen instances.…”

Section: Hyperparameter Tuningmentioning

confidence: 99%

“…Advances on MPC-based training of tree based classifiers are fairly limited. While there is work on secure inference with pre-trained decision trees and tree ensembles [7][8][9], work on secure training itself is limited to the training of individual decision trees (DTs). Several authors have proposed a secure version of Quinlan's ID3 algorithm [10] for training DTs with categorical features [11][12][13][14].…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Privacy-preserving training of tree ensembles over continuous data

Adams

Choudhary

Cock

et al. 2022

Proceedings on Privacy Enhancing Technologies

Self Cite

View full text Add to dashboard Cite

Most existing Secure Multi-Party Computation (MPC) protocols for privacy-preserving training of decision trees over distributed data assume that the features are categorical. In real-life applications, features are often numerical. The standard “in the clear” algorithm to grow decision trees on data with continuous values requires sorting of training examples for each feature in the quest for an optimal cut-point in the range of feature values in each node. Sorting is an expensive operation in MPC, hence finding secure protocols that avoid such an expensive step is a relevant problem in privacy-preserving machine learning. In this paper we propose three more efficient alternatives for secure training of decision tree based models on data with continuous features, namely: (1) secure discretization of the data, followed by secure training of a decision tree over the discretized data; (2) secure discretization of the data, followed by secure training of a random forest over the discretized data; and (3) secure training of extremely randomized trees (“extra-trees”) on the original data. Approaches (2) and (3) both involve randomizing feature choices. In addition, in approach (3) cut-points are chosen randomly as well, thereby alleviating the need to sort or to discretize the data up front. We implemented all proposed solutions in the semi-honest setting with additive secret sharing based MPC. In addition to mathematically proving that all proposed approaches are correct and secure, we experimentally evaluated and compared them in terms of classification accuracy and runtime. We privately train tree ensembles over data sets with thousands of instances or features in a few minutes, with accuracies that are at par with those obtained in the clear. This makes our solution more efficient than the existing approaches, which are based on oblivious sorting.

show abstract

Section: Hyperparameter Tuningmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Privacy-preserving training of tree ensembles over continuous data

Adams

Choudhary

Cock

et al. 2022

Proceedings on Privacy Enhancing Technologies

Self Cite

View full text Add to dashboard Cite

show abstract

“…Secure multiparty computation(SMC) for privacy preservation that do computations on encrypted data with personally identifiable information had opened a new dimension. Data is a very precious commodity, therefore techniques like privacy preserving scoring of Tree Ensembles [36] are designed to provide a framework that provides cryptographic protocols for sending data securely.…”

Section: Security/privacy Frameworkmentioning

confidence: 99%

Systematic Mapping Study of AI/Machine Learning in Healthcare and Future Directions

2021

View full text Add to dashboard Cite

This study attempts to categorise research conducted in the area of: use of machine learning in healthcare, using a systematic mapping study methodology. In our attempt, we reviewed literature from top journals, articles, and conference papers by using the keywords use of machine learning in healthcare. We queried Google Scholar, resulted in 1400 papers, and then categorised the results on the basis of the objective of the study, the methodology adopted, type of problem attempted and disease studied. As a result we were able to categorize study in five different categories namely, interpretable ML, evaluation of medical images, processing of EHR, security/privacy framework, and transfer learning. In the study we also found that most of the authors have studied cancer, and one of the least studied disease was epilepsy, evaluation of medical images is the most researched and a new field of research, Interpretable ML/Explainable AI, is gaining momentum. Our basic intent is to provide a fair idea to future researchers about the field and future directions.

show abstract

“…In social networks, systems are develop that decide (semi-)automatically whether to share information with others [3]. Frameworks for privacy-preserving methods in healthcare are also in development [8]. Classification protocols that ensure confidentiality of both data and classifier are described in [5] and implemented by modification of existing protocols.…”

Section: Related Workmentioning

confidence: 99%

Supervised Machine Learning with Plausible Deniability

Rass,

König,

Wachter

et al. 2021

Preprint

View full text Add to dashboard Cite

We study the question of how well machine learning (ML) models trained on a certain data set provide privacy for the training data, or equivalently, whether it is possible to reverse-engineer the training data from a given ML model. While this is easy to answer negatively in the most general case, it is interesting to note that the protection extends over non-recoverability towards plausible deniability: Given an ML model f , we show that one can take a set of purely random training data, and from this define a suitable "learning rule" that will produce a ML model that is exactly f . Thus, any speculation about which data has been used to train f is deniable upon the claim that any other data could have led to the same results. We corroborate our theoretical finding with practical examples, and open source implementations of how to find the learning rules for a chosen set of raining data.

show abstract

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

Cited by 36 publications

References 28 publications

Privacy-preserving training of tree ensembles over continuous data

Privacy-preserving training of tree ensembles over continuous data

Systematic Mapping Study of AI/Machine Learning in Healthcare and Future Directions

Supervised Machine Learning with Plausible Deniability

Contact Info

Product

Resources

About