aiqbench analysis
This research advances the intersection of machine learning and cryptography by enabling the training of convolutional neural networks on secret-shared single-cell data without exposing sensitive patient information. The proposed secure multi-party computation framework successfully retains critical model components like ReLU activations, outperforming previous privacy-preserving baselines that required architectural simplifications. By allowing diverse institutional collaboration while maintaining strict data confidentiality, this work addresses a major bottleneck in developing robust models for rare disease detection.
Privacy-Preserving Detection of Rare Disease-Associated Cell Subsets via Secure Multi-Party Computation
arXiv:2608.20118v1 Announce Type: cross Abstract: The detection of rare disease-associated cell subsets from high-dimensional single-cell measurements is critical for understanding diseases such as leukaemia and viral infections. CellCnn, a convolutional neural network (CNN) designed for this task, has demonstrated the ability to identify phenotype-associated cell populations at frequencies as low as 0.01\%. Training such models reliably requires patient cohorts that are larger and more diverse than any single institution can typically assemble, and the underlying single-cell data is too sensitive to share across institutional boundaries under existing privacy regulations. We propose a secure multi-party computation (MPC) framework that enables the training and inference of CellCnn entirely on secret-shared data. This ensures that neither the participants nor the computing servers ever observe raw patient data or intermediate values. Evaluated on benchmark single-cell datasets for cytomegalovirus infection (CMV) and acute myeloid leukaemia (AML), our implementation preserves accuracy close to its plaintext counterpart while outperforming the prior privacy-preserving baseline. In contrast to earlier privacy-preserving approaches that removed components such as ReLU activations and bias terms, our method retains these key parts of the CellCnn architecture and supports accurate analysis without exposing raw patient data.
Abstract:The detection of rare disease-associated cell subsets from high-dimensional single-cell measurements is critical for understanding diseases such as leukaemia and viral infections. CellCnn, a convolutional neural network (CNN) designed for this task, has demonstrated the ability to identify phenotype-associated cell populations at frequencies as low as 0.01\%. Training such models reliably requires patient cohorts that are larger and more diverse than any single institution can typically assemble, and the underlying single-cell data is too sensitive to share across institutional boundaries under existing privacy regulations. We propose a secure multi-party computation (MPC) framework that enables the training and inference of CellCnn entirely on secret-shared data. This ensures that neither the participants nor the computing servers ever observe raw patient data or intermediate values. Evaluated on benchmark single-cell datasets for cytomegalovirus infection (CMV) and acute myeloid leukaemia (AML), our implementation preserves accuracy close to its plaintext counterpart while outperforming the prior privacy-preserving baseline. In contrast to earlier privacy-preserving approaches that removed components such as ReLU activations and bias terms, our method retains these key parts of the CellCnn architecture and supports accurate analysis without exposing raw patient data.
Cryptography and Security (cs.CR); Machine Learning (cs.LG)
arXiv:2608.20118 [cs.CR]
(or arXiv:2608.20118v1 [cs.CR] for this version)
https://doi.org/10.48550/arXiv.2608.20118 Focus to learn more arXiv-issued DOI via DataCite
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Full text under the publisher's open licence · 282 words
Related coverage
I Did This Without Your Knowledge
LessWrong · Oct 17, 2026
Disentangling Latent Risk Pathways via Bayesian Hypergraph Inference
arXiv · Jun 9, 2026
Making Single-Cell Data Distillation Auditable: Traceable Real-Cell Coresets via Discrete Min-Max Selection
arXiv · Jul 23, 2026
How to build a cancer vaccine, and whether they will work this time
LessWrong · Jun 8, 2026