Defending against Reconstruction Attacks through Differentially Private Federated Learning for Classification of Heterogeneous Chest X-ray Data

Ziegler, Joceline; Pfitzner, Bjarne; Schulz, Heinrich; Saalbach, Axel; Arnrich, Bert

doi:10.3390/s22145195

Cited by 11 publications

(7 citation statements)

References 56 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Even more, we find that the trade-off between privacy risks and model performance vanishes when using such large but protective privacy budgets. It is known from previous works 23,[36][37][38] that PETs formally protect AI models in sensitive contexts from reconstruction attacks. While we note that our results are empirical, it is apparent that DP training with minimal guarantees still provides better protection than non-private training.…”

Section: Discussionmentioning

confidence: 99%

Reconciling privacy and accuracy in AI for medical imaging

Ziller,

Mueller,

Stieger

et al. 2024

Nat Mach Intell

View full text Add to dashboard Cite

Artificial intelligence (AI) models are vulnerable to information leakage of their training data, which can be highly sensitive, for example, in medical imaging. Privacy-enhancing technologies, such as differential privacy (DP), aim to circumvent these susceptibilities. DP is the strongest possible protection for training models while bounding the risks of inferring the inclusion of training samples or reconstructing the original data. DP achieves this by setting a quantifiable privacy budget. Although a lower budget decreases the risk of information leakage, it typically also reduces the performance of such models. This imposes a trade-off between robust performance and stringent privacy. Additionally, the interpretation of a privacy budget remains abstract and challenging to contextualize. Here we contrast the performance of artificial intelligence models at various privacy budgets against both theoretical risk bounds and empirical success of reconstruction attacks. We show that using very large privacy budgets can render reconstruction attacks impossible, while drops in performance are negligible. We thus conclude that not using DP at all is negligent when applying artificial intelligence models to sensitive data. We deem our results to lay a foundation for further debates on striking a balance between privacy risks and model performance.

show abstract

Section: Discussionmentioning

confidence: 99%

Reconciling privacy and accuracy in AI for medical imaging

Ziller,

Mueller,

Stieger

et al. 2024

Nat Mach Intell

View full text Add to dashboard Cite

show abstract

“…Data composition, distribution, and reconciliation are the next overarching theme of FL research topics. For a summary of the different kinds of attacks and more information regarding the security-based implementations, please reference the following reviews [9,11,32,33]…”

Section: Securitymentioning

confidence: 99%

“…Ziegler et al evaluated the feasibility of differential private FL on chest X-ray classification [32]. The group focused on the security aspect of FL by introducing Reyni differential privacy with Gaussian noise into the local training model.…”

Section: General Chest X-raysmentioning

confidence: 99%

Medical Imaging Applications of Federated Learning

Sandhu,

Gorji,

Tavakolian

et al. 2023

Diagnostics

View full text Add to dashboard Cite

Since its introduction in 2016, researchers have applied the idea of Federated Learning (FL) to several domains ranging from edge computing to banking. The technique’s inherent security benefits, privacy-preserving capabilities, ease of scalability, and ability to transcend data biases have motivated researchers to use this tool on healthcare datasets. While several reviews exist detailing FL and its applications, this review focuses solely on the different applications of FL to medical imaging datasets, grouping applications by diseases, modality, and/or part of the body. This Systematic Literature review was conducted by querying and consolidating results from ArXiv, IEEE Xplorer, and PubMed. Furthermore, we provide a detailed description of FL architecture, models, descriptions of the performance achieved by FL models, and how results compare with traditional Machine Learning (ML) models. Additionally, we discuss the security benefits, highlighting two primary forms of privacy-preserving techniques, including homomorphic encryption and differential privacy. Finally, we provide some background information and context regarding where the contributions lie. The background information is organized into the following categories: architecture/setup type, data-related topics, security, and learning types. While progress has been made within the field of FL and medical imaging, much room for improvement and understanding remains, with an emphasis on security and data issues remaining the primary concerns for researchers. Therefore, improvements are constantly pushing the field forward. Finally, we highlighted the challenges in deploying FL in medical imaging applications and provided recommendations for future directions.

show abstract

“…Among the seven selected articles about X-ray images, all of them used CNNs, six used pre-trained models, and almost half of them applied more than one pre-trained model to compare results [21,22,26]. They used ResNet18 and ResNet34, DenseNet121 and ResNet50, VGG-16, and ResNet50, respectively, and share some common models.…”

Section: Magnetic Resonance Imagingmentioning

confidence: 99%

Federated Learning in Medical Image Analysis: A Systematic Survey

da Silva,

Camacho,

Tavares

2023

Electronics

View full text Add to dashboard Cite

Medical image analysis is crucial for the efficient diagnosis of many diseases. Typically, hospitals maintain vast repositories of images, which can be leveraged for various purposes, including research. However, access to such image collections is largely restricted to safeguard the privacy of the individuals whose images are being stored, as data protection concerns come into play. Recently, the development of solutions for Automated Medical Image Analysis has gained significant attention, with Deep Learning being one solution that has achieved remarkable results in this area. One promising approach for medical image analysis is Federated Learning (FL), which enables the use of a set of physically distributed data repositories, usually known as nodes, satisfying the restriction that the data do not leave the repository. Under these conditions, FL can build high-quality, accurate deep-learning models using a lot of available data wherever it is. Therefore, FL can help researchers and clinicians diagnose diseases and support medical decisions more efficiently and robustly. This article provides a systematic survey of FL in medical image analysis, specifically based on Magnetic Resonance Imaging, Computed Tomography, X-radiography, and histology images. Hence, it discusses applications, contributions, limitations, and challenges and is, therefore, suitable for those who want to understand how FL can contribute to the medical imaging domain.

show abstract

Defending against Reconstruction Attacks through Differentially Private Federated Learning for Classification of Heterogeneous Chest X-ray Data

Cited by 11 publications

References 56 publications

Reconciling privacy and accuracy in AI for medical imaging

Reconciling privacy and accuracy in AI for medical imaging

Medical Imaging Applications of Federated Learning

Federated Learning in Medical Image Analysis: A Systematic Survey

Contact Info

Product

Resources

About