paper-with-me

홈 › Papers

Privacy-Utility Trade-offs in Neural Networks for Medical Population Graphs: Insights from Differential Privacy and Graph Structure

2023-07-13 · Tamara T. Mueller, Maulik Chevli, Ameya Daigavane, Daniel Rueckert, Georgios Kaissis

We initiate an empirical investigation into differentially private graph neural networks on population graphs from the medical domain by examining privacy-utility trade-offs at different privacy levels on both real-world and synthetic datasets and performing auditing through membership inference attacks. Our findings highlight the potential and the challenges of this specific DP application area. Moreover, we find evidence that the underlying graph structure constitutes a potential factor for larger performance gaps by showing a correlation between the degree of graph homophily and the accuracy of the trained model.

📄 PDF Abstract BibTeX arXiv:2307.06760

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Can large language models be privacy preserving and fair medical coders?

2024-12-07 · Ali Dadsetan, Dorsa Soleymani, Xijie Zeng, Frank Rudzicz

Protecting patient data privacy is a critical concern when deploying machine learning algorithms in healthcare. Differential privacy (DP) is a common method for preserving privacy in such settings and, in this work, we e…

FairnessPrivacy Preserving

Evaluating Trade-offs in Computer Vision Between Attribute Privacy, Fairness and Utility

2023-02-15 · William Paul, Philip Mathew, Fady Alajaji, Philippe Burlina

This paper investigates to what degree and magnitude tradeoffs exist between utility, fairness and attribute privacy in computer vision. Regarding privacy, we look at this important problem specifically in the context of…

AttributeFairness

Auditing Fairness-Privacy Trade-offs: Subpopulation-Level Effects of Fairness-Enhancing Algorithms

2026-07-16 · Umid Suleymanov, Ilhama Novruzova, Khalid Mammadov, Natavan Hasanova 외 arxiv

Machine learning (ML) models deployed in sensitive domains such as healthcare, law enforcement, and finance must satisfy not only utility requirements but also fairness and privacy guarantees. While prior work has largel…

DP-SGD vs PATE: Which Has Less Disparate Impact on Model Accuracy?

2021-06-22 · Archit Uniyal, Rakshit Naidu, Sasikanth Kotti, Sahib Singh 외

Recent advances in differentially private deep learning have demonstrated that application of differential privacy, specifically the DP-SGD algorithm, has a disparate impact on different sub-groups in the population, whi…

Deep LearningFairness

Efficient Public Verification of Private ML via Regularization

2025-12-03 · Zoë Ruha Bell, Anvith Thudi, Olive Franzese-McLaughlin, Nicolas Papernot 외 arxiv

Training with differential privacy (DP) guarantees dataset members that they cannot be identified by users of the released model. However, those data providers, and, in general, the public, lack methods to efficiently ve…