Boosting Privately: Federated Extreme Gradient Boosting for Mobile Crowdsensing

Liu, Yang; Ma, Zhuo; Liu, Ximeng; Ma, Siqi; Nepal, Surya; Deng, Robert H.; Ren, Kui

doi:10.1109/icdcs47774.2020.00017

Cited by 69 publications

(46 citation statements)

References 17 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Then each party receives a single point from this function, and k of those points can be used to compute the function equation and subsequently take the y-axis intersection as the secret. Secret sharing has been used for FL by Bonawitz et al [6] and Liu et al [46] to securely compute aggregate parameter values. In contrast, Zhang et al [76] adopt this method to distribute a private encryption key to multiple clients.…”

Section: (Additively) Homomorphicmentioning

confidence: 99%

Federated Learning in a Medical Context: A Systematic Literature Review

Pfitzner

Steckhan

Arnrich

2021

ACM Trans. Internet Technol.

123

View full text Add to dashboard Cite

Data privacy is a very important issue. Especially in fields like medicine, it is paramount to abide by the existing privacy regulations to preserve patients’ anonymity. However, data is required for research and training machine learning models that could help gain insight into complex correlations or personalised treatments that may otherwise stay undiscovered. Those models generally scale with the amount of data available, but the current situation often prohibits building large databases across sites. So it would be beneficial to be able to combine similar or related data from different sites all over the world while still preserving data privacy. Federated learning has been proposed as a solution for this, because it relies on the sharing of machine learning models, instead of the raw data itself. That means private data never leaves the site or device it was collected on. Federated learning is an emerging research area, and many domains have been identified for the application of those methods. This systematic literature review provides an extensive look at the concept of and research into federated learning and its applicability for confidential healthcare datasets.

show abstract

Section: (Additively) Homomorphicmentioning

confidence: 99%

Federated Learning in a Medical Context: A Systematic Literature Review

Pfitzner

Steckhan

Arnrich

2021

ACM Trans. Internet Technol.

123

View full text Add to dashboard Cite

show abstract

“…For example, Aono et al [23] used homomorphic encryption to improve the logistic regression algorithm ensuring the security of the training and predicting data. Liu et al [24] propose a secret sharing-based federated extreme boosting learning framework to achieve privacypreserving model training for mobile crowdsensing. Xu et al [25] proposed a privacy-preserving and verifiable federated learning framework based on homomorphic hash functions, in which clients can verify whether the result returned by cloud server is correct.…”

Section: Related Workmentioning

confidence: 99%

Privacy‐Preserving Federated Learning Framework with General Aggregation and Multiparty Entity Matching

Zhou

Tian

Peng

2021

Wireless Communications and Mobile Computing

View full text Add to dashboard Cite

The requirement for data sharing and privacy has brought increasing attention to federated learning. However, the existing aggregation models are too specialized and deal less with users’ withdrawal issue. Moreover, protocols for multiparty entity matching are rarely covered. Thus, there is no systematic framework to perform federated learning tasks. In this paper, we systematically propose a privacy-preserving federated learning framework (PFLF) where we first construct a general secure aggregation model in federated learning scenarios by combining the Shamir secret sharing with homomorphic cryptography to ensure that the aggregated value can be decrypted correctly only when the number of participants is greater than t . Furthermore, we propose a multiparty entity matching protocol by employing secure multiparty computing to solve the entity alignment problems and a logistic regression algorithm to achieve privacy-preserving model training and support the withdrawal of users in vertical federated learning (VFL) scenarios. Finally, the security analyses prove that PFLF preserves the data privacy in the honest-but-curious model, and the experimental evaluations show PFLF attains consistent accuracy with the original model and demonstrates the practical feasibility.

show abstract

“…Kikuchi et al combine SMC [41] and HE [167] approaches, and they design a secure scalar product protocol that incurs low communication costs and does not require a trusted setup [96]. For XGBoost, several works use HE and secret sharing to protect the local intermediate residuals [118,119,175]. Liu et al [118] propose an aggregation scheme that, with Shamir secret sharing and Paillier HE, ensures that the aggregator cannot access individual party updates.…”

Section: Secure Multiparty Computation Du and Zhanmentioning

confidence: 99%

“…For XGBoost, several works use HE and secret sharing to protect the local intermediate residuals [118,119,175]. Liu et al [118] propose an aggregation scheme that, with Shamir secret sharing and Paillier HE, ensures that the aggregator cannot access individual party updates. Each party locally computes gradients and the aggregator derives the score of each party's split to select in clear the best one.…”

Section: Secure Multiparty Computation Du and Zhanmentioning

confidence: 99%

“…Their solution yields a more accurate model than others that employ local DP, as the amount of noise is divided by the number of parties required to "unlock" the HE threshold. Subsequently, Liu et al [118] improved this approach by ensuring that the aggregation is performed correctly. Moreover, combining local DP and secure aggregation with threshold HE [21] is envisioned in both horizontal and vertical data partitioning settings for XGBoost [162].…”

Section: Hybrid Solutionsmentioning

confidence: 99%

See 1 more Smart Citation

SoK: Privacy-Preserving Collaborative Tree-based Model Learning

Chatel

Pyrgelis

Troncoso-Pastoriza

et al. 2021

Proceedings on Privacy Enhancing Technologies

View full text Add to dashboard Cite

Tree-based models are among the most efficient machine learning techniques for data mining nowadays due to their accuracy, interpretability, and simplicity. The recent orthogonal needs for more data and privacy protection call for collaborative privacy-preserving solutions. In this work, we survey the literature on distributed and privacy-preserving training of tree-based models and we systematize its knowledge based on four axes: the learning algorithm, the collaborative model, the protection mechanism, and the threat model. We use this to identify the strengths and limitations of these works and provide for the first time a framework analyzing the information leakage occurring in distributed tree-based model learning.

show abstract

Boosting Privately: Federated Extreme Gradient Boosting for Mobile Crowdsensing

Cited by 69 publications

References 17 publications

Federated Learning in a Medical Context: A Systematic Literature Review

Federated Learning in a Medical Context: A Systematic Literature Review

Privacy‐Preserving Federated Learning Framework with General Aggregation and Multiparty Entity Matching

SoK: Privacy-Preserving Collaborative Tree-based Model Learning

Contact Info

Product

Resources

About