PrizeiDASH Privacy & Security Workshop · 2026
Team PPML Huskies won the track on accelerating deep learning under secure multi-party computation (MPC). Each team ran a drug-target interaction predictor on secret shares held by two parties. Entries had to stay within 2% of the original model’s accuracy and were ranked by speedup.
PaperNeurIPS · 2026
Steven Golob, Patrick McKeever, Sikha Pentyala, Martine De Cock, Jonathan Peck
A membership inference attack that succeeds against synthetic single-cell RNA-seq data. The attack was validated independently in the CAMDA Health Privacy Challenge at ISMB 2026.
Code →
PrizeCAMDA at ISMB · 2026
First prize, CAMDA 2026 Health Privacy Challenge, Track 1
Charlene Jarrell, Daniil Filienko, Jonathan Kim, Emma Szebenyi, Sikha Pentyala, Steven Golob, Martine De Cock
Awarded for “Does Synthetic Bulk RNA-seq Data Protect Donors? Privacy Auditing through Membership Inference Attacks.” The talk also won best presentation at the CAMDA workshop.
Trophy ceremony (LinkedIn) →
PrizeCAMDA at ISMB · 2026
Winner, CAMDA 2026 Health Privacy Challenge, Track 2
Steven Golob, Patrick McKeever, Sikha Pentyala, Martine De Cock, Jonathan Peck
Awarded for “Privacy Auditing of Synthetic Single-Cell RNA-seq Data.”
Write-up (Google Scholar) →
PaperProceedings on Privacy Enhancing Technologies (PoPETs) · 2027
Steven Golob, Sikha Pentyala, Martine De Cock
An overview of reconstruction attacks on synthetic tabular data, including the attack with which team PPML Huskies won the red-team challenge of the NIST Collaborative Research Cycle in 2025.
PaperICML · 2026
Mayank Kumar, Qian Lou, Paulo L. Barreto, Martine De Cock, Sikha Pentyala
The first paper on generating synthetic data with fully homomorphic encryption. Joint work with the University of Central Florida.
PaperJournal of Computational Biology · 2026
Daniil Filienko, Martine De Cock, Sikha Pentyala
Several data custodians train one RNA-seq generator together using secure multi-party computation, so that no custodian discloses its records to the others or to a server. Also given as a talk at RECOMB-Privacy 2026.
Code →
PaperACM-BCB (oral presentation) · 2026
Sikha Pentyala, Abhinava Bharathi Babu, Joseph C. Ahn, Martine De Cock
Federated synthetic data generation with secure multi-party computation for liver disease research, evaluated on data from the United Network for Organ Sharing (UNOS). Joint work with Mayo Clinic.
PosterACM-BCB · 2026
Sikha Pentyala, Ziwei Pan, Patrick J. McKeever, Jineta Banerjee, Luca Foschini, Martine De Cock
Generating synthetic germline variant call files for neurofibromatosis type 1. Joint work with Sage Bionetworks.
PDF →
PosterRECOMB-Privacy · 2026
Sikha Pentyala, Ziwei Pan, Luca Foschini, Martine De Cock, Jineta Banerjee
Joint work with Sage Bionetworks.
Press & mediaNAIRR Pilot · 2026
A NAIRR Pilot feature on the project, published February 2026.
Press & mediaUniversity of Washington Tacoma (video) · 2026
UW Tacoma story →
PrizeCAMDA · 2025
The UW Tacoma and Sage Bionetworks team placed first in the track for bulk RNA-seq synthetic data generation and second in the track for single-cell RNA-seq.