PPML-Omics: a Privacy-Preserving federated Machine Learning method protects patients’ privacy in omic data

Abstract

Modern machine learning models towards various tasks with omic data analysis give rise to threats of privacy leakage of patients involved in those datasets. Despite the advances in different privacy technologies, existing methods tend to introduce too much noise, which hampers model accuracy and usefulness. Here, we built a secure and privacy-preserving machine learning (PPML) system by combining federated learning (FL), differential privacy (DP) and shuffling mechanism. We applied this system to analyze data from three sequencing technologies, and addressed the privacy concern in three major tasks of omic data, namely cancer classification with bulk RNA-seq, clustering with single-cell RNA-seq, and the integration of spatial gene expression and tumour morphology with spatial transcriptomics, under three representative deep learning models. We also examined privacy breaches in depth through privacy attack experiments and demonstrated that our PPML-Omics system could protect patients' privacy. In each of these applications, PPML-Omics was able to outperform state-of-the-art systems under the same level of privacy guarantee, demonstrating the versatility of the system in simultaneously balancing the privacy-preserving capability and utility in omic data analysis. Furthermore, we gave the theoretical proof of the privacy-preserving capability of PPML-Omics, suggesting the first mathematically guaranteed model with robust and generalizable empirical performance.

Audit to Forget: A Unified Method to Revoke Patients’ Private Data in Intelligent Healthcare

“…Meanwhile, those aforementioned regulations will force involved third parties to take actions immediately. According to the requirements of those regulations, not only the previously authorized data by individuals need to be deleted immediately from hosts' storage systems but also 1 Computer Science Program, Computer, Electrical and Mathematical Sciences the associated information should be removed from DL models trained with those data, because DL models could memorize sensitive information of training data and thus expose individual's privacy under risk [7], [8], [9], [10], [11].…”

Pre-trained Multimodal Large Language Model Enhances Dermatological Diagnosis using SkinGPT-4

“…However, their proposed vision-text models were limited to certain tasks. Meanwhile, for ChatCAD, users need to use ChatGPT’s API to upload text descriptions, which could raise data privacy issues [41], [53], [54] as both medical images and text descriptions contain a lot of patients’ private information [55], [56], [57], [58]. To address those issues, MiniGPT-4 [59] is the first open-source method that allows users to deploy locally to interface images with state-of-the-art LLMs and interact using natural language without the need to fine-tune both pre-trained large models but only a small alignment layer.…”

scFed: federated learning for cell type classification with scRNA-seq

“…scPrivacy utilized federated deep metric learning algorithms to train the federated cell type identification model on multiple institutional datasets in data privacy protection manner [ 6 ]. PPML-Omics [ 7 ] analyzed data from three sequencing technologies with a privacy-preserving federated framework, clustering cell populations with Auto-encoder and k-means clustering. Those approaches align with the growing emphasis on ensuring data privacy in bioinformatics, as underscored by the challenges and concerns presented in the field.…”