Encrypted federated learning for secure decentralized collaboration in cancer image analysis

Medical Image Analysis, Journal Year: 2023, Volume and Issue: 92, P. 103059 - 103059

Published: Dec. 7, 2023

Artificial intelligence (AI) has a multitude of applications in cancer research and oncology. However, the training AI systems is impeded by limited availability large datasets due to data protection requirements other regulatory obstacles. Federated swarm learning represent possible solutions this problem collaboratively models while avoiding transfer. these decentralized methods, weight updates are still transferred aggregation server for merging models. This leaves possibility breach privacy, example model inversion or membership inference attacks untrusted servers. Somewhat-homomorphically-encrypted federated (SHEFL) solution because only encrypted weights transferred, performed space. Here, we demonstrate first successful implementation SHEFL range clinically relevant tasks image analysis on multicentric radiology histopathology. We show that enables which outperform locally trained perform par with centrally trained. In future, can enable multiple institutions co-train without forsaking governance ever transmitting any decryptable

Language: Английский

---

Recent methodological advances in federated learning for healthcare

Patterns, Journal Year: 2024, Volume and Issue: 5(6), P. 101006 - 101006

Published: June 1, 2024

For healthcare datasets, it is often impossible to combine data samples from multiple sites due ethical, privacy, or logistical concerns. Federated learning allows for the utilization of powerful machine algorithms without requiring pooling data. Healthcare have many simultaneous challenges, such as highly siloed data, class imbalance, missing distribution shifts, and non-standardized variables, that require new methodologies address. adds significant methodological complexity conventional centralized learning, distributed optimization, communication between nodes, aggregation models, redistribution models. In this systematic review, we consider all papers on Scopus published January 2015 February 2023 describe federated addressing challenges with We reviewed 89 meeting these criteria. Significant systemic issues were identified throughout literature, compromising reviewed. give detailed recommendations help improve methodology development in healthcare.

Language: Английский

---

From challenges and pitfalls to recommendations and opportunities: Implementing federated learning in healthcare

Medical Image Analysis, Journal Year: 2025, Volume and Issue: 101, P. 103497 - 103497

Published: Feb. 14, 2025

Federated learning holds great potential for enabling large-scale healthcare research and collaboration across multiple centers while ensuring data privacy security are not compromised. Although numerous recent studies suggest or utilize federated based methods in healthcare, it remains unclear which ones have clinical utility. This review paper considers analyzes the most up to May 2024 that describe healthcare. After a thorough review, we find vast majority appropriate use due their methodological flaws and/or underlying biases include but limited concerns, generalization issues, communication costs. As result, effectiveness of is significantly To overcome these challenges, provide recommendations promising opportunities might be implemented resolve problems improve quality model development with

Language: Английский

---

Secure and federated genome-wide association studies for biobank-scale datasets

Nature Genetics, Journal Year: 2025, Volume and Issue: unknown

Published: Feb. 24, 2025

Sharing data across institutions for genome-wide association studies (GWAS) would enhance the discovery of genetic variation linked to health and disease1,2. However, existing data-sharing regulations limit scope such collaborations3. Although cryptographic tools secure computation promise enable collaborative analysis with formal privacy guarantees, approaches either are computationally impractical or do not implement current state-of-the-art methods4–6. We introduce federated (SF-GWAS), a combination frameworks distributed algorithms that empowers efficient accurate GWAS on private held by multiple entities while ensuring confidentiality. SF-GWAS supports widely used pipelines based principal-component linear mixed models. demonstrate accuracy practical runtimes five datasets, including UK Biobank cohort 410,000 individuals, showcasing an order-of-magnitude improvement in runtime compared previous methods. Our work enables genomic at unprecedented scale. is workflow secure, studies, implementing accurate, privacy-preserving analysis, linear/logistic regression model methods biobank-scale multisite analyses.

Language: Английский

---

Scalable and Privacy-Preserving Federated Principal Component Analysis

2022 IEEE Symposium on Security and Privacy (SP), Journal Year: 2023, Volume and Issue: unknown

Published: May 1, 2023

Principal component analysis (PCA) is an essential algorithm for dimensionality reduction in many data science domains. We address the problem of performing a federated PCA on private distributed among multiple providers while ensuring confidentiality. Our solution, SF-PCA, end-to-end secure system that preserves confidentiality both original and all intermediate results passive-adversary model with up to all-but-one colluding parties. SF-PCA jointly leverages multiparty homomorphic encryption, interactive protocols, edge computing efficiently interleave computations local cleartext operations collectively encrypted data. obtains as accurate non-secure centralized solutions, independently distribution It scales linearly or better dataset dimensions number providers. more precise than existing approaches approximate solution by combining results, between 3x 250x faster privacy-preserving alternatives based solely computation encryption. work demonstrates practical applicability datasets.

Language: Английский

---

Unified fair federated learning for digital healthcare

Patterns, Journal Year: 2023, Volume and Issue: 5(1), P. 100907 - 100907

Published: Dec. 28, 2023

Federated learning (FL) is a promising approach for healthcare institutions to train high-quality medical models collaboratively while protecting sensitive data privacy. However, FL encounter fairness issues at diverse levels, leading performance disparities across different subpopulations. To address this, we propose Learning with Unified Fairness Objective (FedUFO), unified framework consolidating levels within FL. By leveraging distributionally robust optimization and uncertainty set, it ensures consistent all subpopulations enhances the overall efficacy of in other domains maintaining accuracy comparable those existing methods. Our model was validated by applying four digital tasks using real-world datasets federated settings. collaborative machine paradigm not only promotes artificial intelligence but also fosters social equity embodying fairness.

Language: Английский

---

Privacy-Enhancing Technologies in Biomedical Data Science

Annual Review of Biomedical Data Science, Journal Year: 2024, Volume and Issue: 7(1), P. 317 - 343

Published: Aug. 23, 2024

The rapidly growing scale and variety of biomedical data repositories raise important privacy concerns. Conventional frameworks for collecting sharing human subject offer limited protection, often necessitating the creation silos. Privacy-enhancing technologies (PETs) promise to safeguard these broaden their usage by providing means share analyze sensitive while protecting privacy. Here, we review prominent PETs illustrate role in advancing biomedicine. We describe key use cases latest technical advances highlight recent applications a range domains. conclude discussing outstanding challenges social considerations that need be addressed facilitate broader adoption science.

Language: Английский

---

USE OF ARTIFICIAL INTELLIGENCE AND AUDIT ANALYTICS IN INTERNAL AUDIT PROCESSES IN THE PUBLIC SECTOR

EDPACS, Journal Year: 2024, Volume and Issue: 69(9), P. 1 - 15

Published: July 9, 2024

The impact of digitization on management processes in the public sector has led to changes their roles, corporate activities, objectives, and requirements. Consequently, as scope responsibilities have changed expanded due digitization, organization, storage, processing increasing dimension data resulting from services become more complex. This also accelerated handling artificial intelligence internal audits sector. In sector, large related citizens personal information, tenders, contracts, suppliers makes it difficult control oversee this data. Therefore, there is a trend handle Public Sector Internal Audit Artificial Intelligence models audit analytics facilitate while automating monitoring tracking activities. From viewpoint, study explores advantages audit. attempts contribute literature by providing policy recommendations for professionals researchers.

Language: Английский

---

Secure and Federated Genome-Wide Association Studies for Biobank-Scale Datasets

bioRxiv (Cold Spring Harbor Laboratory), Journal Year: 2022, Volume and Issue: unknown

Published: Dec. 2, 2022

ABSTRACT Sharing data across institutions for genome-wide association studies (GWAS) would enhance the discovery of genetic variants linked to health and disease 1, 2 . However, existing sharing regulations limit scope such collaborations 3 Although cryptographic tools secure computation promise enable collaborative analysis with formal privacy guarantees, approaches either are computationally impractical or support only simplified analyses 4–7 We introduce federated (SF-GWAS), a novel combination frameworks distributed algorithms that empowers efficient accurate GWAS on private held by multiple entities while ensuring confidentiality. SF-GWAS supports most widely-used pipelines based principal component (PCA) linear mixed models (LMMs). demonstrate accuracy practical runtimes five datasets, including large UK Biobank cohort 410K individuals, showcasing an order-of-magnitude improvement in runtime compared previous work. Our work realizes power genomic at unprecedented scale.

Language: Английский

---

Encrypted machine learning of molecular quantum properties

Machine Learning Science and Technology, Journal Year: 2023, Volume and Issue: 4(2), P. 025017 - 025017

Published: April 27, 2023

Abstract Large machine learning (ML) models with improved predictions have become widely available in the chemical sciences. Unfortunately, these do not protect privacy necessary within commercial settings, prohibiting use of potentially extremely valuable data by others. Encrypting prediction process can solve this problem double-blind model evaluation and prohibits extraction training or query data. However, contemporary ML based on fully homomorphic encryption federated are either too expensive for practical to trade higher speed weaker security. We implemented secure computationally feasible encrypted using oblivious transfer enabling molecular quantum properties across compound space. we find that kernel ridge regression a million times more than without encryption. This demonstrates dire need compact architecture, including representation matrix size, minimizes costs.

Language: Английский

---