Davis Railsback's personal web page.
Training Differentially Private Models with Secure Multiparty Computation [pdf][bib]
S. Pentyala, D. Railsback, R. Maia, R. Dowsley, D. Melanson, A. C. A. Nascimento, M. De Cock.
Privacy-Preserving Training of Tree Ensembles over Continuous Data
S. Adams, C. Choudhary, M. De Cock, R. Dowsley, D. Melanson, A. C. A. Nascimento, D. Railsback, J. Shen
Proceedings on Privacy Enhancing Technologies (PoPETS) 2022(2), p. 205-226, 2022
High Performance Logistic Regression for Privacy-Preserving Genome Analysis
M. De Cock, R. Dowsley, A. C. A. Nascimento, D. Railsback, J. Shen, A. Todoki
BMC Medical Genomics 14(23), 2021
Fast Privacy-Preserving Text Classification Based on Secure Multiparty Computation
A. Resende, D. Railsback, R. Dowsley, A. C. A. Nascimento, D. Aranha
IEEE Transactions on Information Forensics and Security (Volume: 17), p. 428-442, 2022
IDASH PRIVACY & SECURITY WORKSHOP 2021 - secure genome analysis competition
Track III - Confidential Computing (task description)
Outcome: 1st place tie with Ant Group, Tencent.
IDASH PRIVACY & SECURITY WORKSHOP 2019 - secure genome analysis competition
Track IV - Secure Collaborative Training of Machine Learning Model (task description)
Outcome: 1st place tie with Alibaba Gemini Lab, Ant Finanical Service Group. Honorable mention: MIT