Reproduce “Protect Your Score: Contact Tracing With Differential Privacy Guarantees” 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
DPFN protects released contact-tracing risk scores by adding calibrated log-normal noise to a combined product of contact messages used by Factorized Neighbors, rather than to each message separately. The authors evaluate it in OpenABM and Covasim simulations. At ε=1, it yields lower peak infection rates than tested private baselines in both simulators; the guarantee is not for unlimited repeated contacts.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.