Reproduce “DNA: Differentially private Neural Augmentation for contact tracing” on OpenResearch

Turn your favorite coding agents into research agents that review literature, develop hypotheses, and run experiments.

Universal app for Apple silicon and Intel. Requires macOS 11 or later.

About this paper

Rob Romijnders, Christos Louizos, Yuki M. Asano, Max Welling

DNA adds a bounded neural correction to a statistical contact-tracing model and adds calibrated Gaussian noise to protect each contact’s message. In OpenABM-Covid19, it reports lower peak infection rate than other tested methods at ε=1 per message. In a separate table comparison, DPFN-S has 52.7 ± 10.9 and DNA 6.4 ± 2.6 infections per thousand under stated test errors. These results are simulated.

Summary by alphaXiv.

Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.