Unlocking Sensitive Data with SPHERE in the Age of AI
- 1Stanford University
Abstract
Sensitive human data underpin discoveries across medicine, biology and the social sciences, yet privacy regulation often prevents sharing them with collaborators or artificial intelligence (AI) systems. We introduce SPHERE, a model-free method that makes sensitive datasets directly usable by AI and shareable for open science as a synthetic twin, while the original records never leave the local environment. Across 33 datasets spanning five scientific domains, SPHERE protects individual privacy against adversarial re-identification attacks while preserving the data's statistical structure: means, variances and correlations are reproduced exactly, effect size and P value in linear statistical analysis is numerically identical, nonlinear machine-learning utility is retained, and each twin is generated in seconds on a laptop. Frontier AI agents running on the twin reach the same scientific conclusions as on the original records. Analyses of the twin reproduce genome- and proteome-wide results at UK Biobank scale and recover the findings of landmark studies across three independent cohorts and consortia. The approach also extends to deep-learning embeddings across language, vision and time-series, with minimal utility loss. We make the Stanford Alzheimer's Disease Research Center cohort openly available for the first time, as a SPHERE twin spanning nine modalities that any registered researcher can analyze without an approval process. We release SPHERE with certification of each twin's privacy and fidelity, and an AI agent that autonomously executes research tasks on sensitive data without ever accessing it. Sensitive datasets that are currently closed to research could thus become routine inputs to open science and AI to enable key discoveries.
Related
- Unlocking the Full Potential of Taylor Dispersion Analysis Through Advanced Detection
- Unlocking oncolytic virotherapy potential: leveraging bacteriophages to conquer immunosuppression
- Unlocking the therapeutic potential of traditional Chinese medicine in Crohn’s disease: from multi-target mechanisms to clinical promise
- BSA101: Unlocking Historical Mutant Collections with BSA-Seq
- Unlocking the secrets of paired terminal genomic repeats utilised by the Burkholderia jumbo phage Matilda
BibTeX
@misc{he2026unlocking,
title = {{Unlocking Sensitive Data with SPHERE in the Age of AI}},
author = {Z. He and J. Park and R. C. Pulgrossi and J. Lee and R. R. Butler and A. Weber and L. Tian and X. Zhang and J. Wang and S. Sha and E. C. Mormino and T. Wyss-Coray and V. W. Henderson and F. M. Longo and J. Zou and M. Desai and R. Altman},
howpublished = {bioRxiv},
year = {2026},
month = sep,
doi = {10.64898/2026.09.01.748580},
url = {https://www.biorxiv.org/content/10.64898/2026.09.01.748580v1},
note = {CC BY-NC-ND},
}
RIS
TY - UNPB
TI - Unlocking Sensitive Data with SPHERE in the Age of AI
AU - Z. He
AU - J. Park
AU - R. C. Pulgrossi
AU - J. Lee
AU - R. R. Butler
AU - A. Weber
AU - L. Tian
AU - X. Zhang
AU - J. Wang
AU - S. Sha
AU - E. C. Mormino
AU - T. Wyss-Coray
AU - V. W. Henderson
AU - F. M. Longo
AU - J. Zou
AU - M. Desai
AU - R. Altman
PY - 2026
DA - 2026/09/01
PB - bioRxiv
DO - 10.64898/2026.09.01.748580
UR - https://www.biorxiv.org/content/10.64898/2026.09.01.748580v1
AB - Sensitive human data underpin discoveries across medicine, biology and the social sciences, yet privacy regulation often prevents sharing them with collaborators or artificial intelligence (AI) systems. We introduce SPHERE, a model-free method that makes sensitive datasets directly usable by AI and shareable for open science as a synthetic twin, while the original records never leave the local environment. Across 33 datasets spanning five scientific domains, SPHERE protects individual privacy against adversarial re-identification attacks while preserving the data's statistical structure: means, variances and correlations are reproduced exactly, effect size and P value in linear statistical analysis is numerically identical, nonlinear machine-learning utility is retained, and each twin is generated in seconds on a laptop. Frontier AI agents running on the twin reach the same scientific conclusions as on the original records. Analyses of the twin reproduce genome- and proteome-wide results at UK Biobank scale and recover the findings of landmark studies across three independent cohorts and consortia. The approach also extends to deep-learning embeddings across language, vision and time-series, with minimal utility loss. We make the Stanford Alzheimer's Disease Research Center cohort openly available for the first time, as a SPHERE twin spanning nine modalities that any registered researcher can analyze without an approval process. We release SPHERE with certification of each twin's privacy and fidelity, and an AI agent that autonomously executes research tasks on sensitive data without ever accessing it. Sensitive datasets that are currently closed to research could thus become routine inputs to open science and AI to enable key discoveries.
ER -