A systematic review on privacy-preserving distributed data mining

Sun, Chang; Ippel, Lianne; Dekker, André; Dumontier, Michel; Soest, Johan van

doi:10.3233/ds-210036

Cited by 9 publications

(7 citation statements)

References 112 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Independently of the belonging category, none of the above-examined approaches consider the problem of data privacy, which remains a critical concern when handling sensitive information such as diabetic data [ 73 ]. FL technology has been utilized in the medical domain to train a prediction model through decentralized data for dealing with different problems [ 74 , 75 , 76 , 77 ].…”

Section: State Of the Artmentioning

confidence: 99%

A Federated Learning-Inspired Evolutionary Algorithm: Application to Glucose Prediction

Falco

Cioppa

Koutný

et al. 2023

Sensors

View full text Add to dashboard Cite

In this paper, we propose an innovative Federated Learning-inspired evolutionary framework. Its main novelty is that this is the first time that an Evolutionary Algorithm is employed on its own to directly perform Federated Learning activity. A further novelty resides in the fact that, differently from the other Federated Learning frameworks in the literature, ours can efficiently deal at the same time with two relevant issues in Machine Learning, i.e., data privacy and interpretability of the solutions. Our framework consists of a master/slave approach in which each slave contains local data, protecting sensible private data, and exploits an evolutionary algorithm to generate prediction models. The master shares through the slaves the locally learned models that emerge on each slave. Sharing these local models results in global models. Being that data privacy and interpretability are very significant in the medical domain, the algorithm is tested to forecast future glucose values for diabetic patients by exploiting a Grammatical Evolution algorithm. The effectiveness of this knowledge-sharing process is assessed experimentally by comparing the proposed framework with another where no exchange of local models occurs. The results show that the performance of the proposed approach is better and demonstrate the validity of its sharing process for the emergence of local models for personal diabetes management, usable as efficient global models. When further subjects not involved in the learning process are considered, the models discovered by our framework show higher generalization capability than those achieved without knowledge sharing: the improvement provided by knowledge sharing is equal to about 3.03% for precision, 1.56% for recall, 3.17% for F1, and 1.56% for accuracy. Moreover, statistical analysis reveals the statistical superiority of model exchange with respect to the case of no exchange taking place.

show abstract

Section: State Of the Artmentioning

confidence: 99%

A Federated Learning-Inspired Evolutionary Algorithm: Application to Glucose Prediction

Falco

Cioppa

Koutný

et al. 2023

Sensors

View full text Add to dashboard Cite

show abstract

“…In this study, we propose a new citizen-centric data platform (called TIDAL) that gives individuals fine-grained access to their data and ensures that citizen-controlled data are processed in a predefined manner. We designed a prototype as a proof-of-concept following an exploratory technology development process in light of our experience in the development of a privacy-preserving distributed data analysis infrastructure in the previous studies [16,29,53,56]. TIDAL consists of an integrated set of components for requesting subsets of data stored in personal data vaults using Solid technologies [35] and analyzing them in a privacy-preserving manner.…”

Section: Introductionmentioning

confidence: 99%

ciTIzen-centric DAta pLatform (TIDAL): Sharing distributed personal data in a privacy-preserving manner for health research

Sun

Ocaña

Soest

et al. 2023

View full text Add to dashboard Cite

Developing personal data sharing tools and standards in conformity with data protection regulations is essential to empower citizens to control and share their health data with authorized parties for any purpose they approve. This can be, among others, for primary use in healthcare, or secondary use for research to improve human health and well-being. Ensuring that citizens are able to make fine-grained decisions about how their personal health data can be used and shared will significantly encourage citizens to participate in more health-related research. In this paper, we propose a ciTIzen-centric DatA pLatform (TIDAL) to give individuals ownership of their own data, and connect them with researchers to donate the use of their personal data for research while being in control of the entire data life cycle, including data access, storage and analysis. We recognize that most existing technologies focus on one particular aspect such as personal data storage, or suffer from executing data analysis over a large number of participants, or face challenges of low data quality and insufficient data interoperability. To address these challenges, the TIDAL platform integrates a set of components for requesting subsets of RDF (Resource Description Framework) data stored in personal data vaults based on SOcial LInked Data (Solid) technology and analyzing them in a privacy-preserving manner. We demonstrate the feasibility and efficiency of the TIDAL platform by conducting a set of simulation experiments using three different pod providers (Inrupt, Solidcommunity, Self-hosted Server). On each pod provider, we evaluated the performance of TIDAL by querying and analyzing personal health data with varying scales of participants and configurations. The reasonable total time consumption and a linear correlation between the number of pods and variables on all pod providers show the feasibility and potential to implement and use the TIDAL platform in practice. TIDAL facilitates individuals to access their personal data in a fine-grained manner and to make their own decision on their data. Researchers are able to reach out to individuals and send them digital consent directly for using personal data for health-related research. TIDAL can play an important role to connect citizens, researchers, and data organizations to increase the trust placed by citizens in the processing of personal data.

show abstract

“…Currently, several privacy protection techniques are available for distributed data mining. These include data perturbation, local learning and global integration, and secure multi-party computation (MPC) [9].…”

Section: Introductionmentioning

confidence: 99%

“…Another PPDDM approach is local learning and global integration. This approach integrates local models into a global model using an ensemble learning technique to improve performance [9]. Each party can train their own local data, which is then integrated to create centralized or global data mining to produce the final result.…”

Section: Introductionmentioning

confidence: 99%

A Reliable Application of MPC for Securing the Tri-Training Algorithm

Kurniawan

Mambo

2023

IEEE Access

View full text Add to dashboard Cite

Due to the widespread use of distributed data mining techniques in a variety of areas, the issue of protecting the privacy of sensitive data has received increasing attention in recent years. Privacypreserving distributed data mining (PPDDM) focuses on decentralized data analysis without the disclosure of sensitive information from data owner. However, the previous PPDDM mostly works on a limited amount of labeled data. In contrast to the real world, unlabeled data is abundance and labeled data is scarce. The objectives of this paper are to study and to analyze privacy-preserving properties of semi-supervised learning (SSL) algorithm with the combination of labeled and unlabeled data, where data is distributed among multiple data owners. In this paper we propose a Privacy-preserving Distributed Data Mining (PPDDM) method by designing a reliable application of secure MPC to semi-supervised tri-training algorithms. We simulate the original tri-training algorithm and tri-training algorithm with secure MPC using a different types of classifiers and datasets. The simulation results show that tri-training in secure MPC has almost same accuracy compared to original tri-training algorithm. We also compare execution time in addition to performance evaluation of tri-training in secure and the original tri-training algorithms.

show abstract

A systematic review on privacy-preserving distributed data mining

Cited by 9 publications

References 112 publications

A Federated Learning-Inspired Evolutionary Algorithm: Application to Glucose Prediction

A Federated Learning-Inspired Evolutionary Algorithm: Application to Glucose Prediction

ciTIzen-centric DAta pLatform (TIDAL): Sharing distributed personal data in a privacy-preserving manner for health research

A Reliable Application of MPC for Securing the Tri-Training Algorithm

Contact Info

Product

Resources

About