AI Paper Atlas

Research map / Federated learning and privacy / Privacy attacks and secure learning

A Scalable Approach for Privacy-Preserving Collaborative Machine Learning

Jinhyun So, Basak Guler, Salman Avestimehr

NeurIPS 2020 · Federated learning and privacy › Privacy attacks and secure learning · approach: Encryption-based private learning · 29 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
replace baseline MPC protocol [BH08] with COPML Lagrange-coded training (Case 1)secure logistic regression training · CIFAR-10, N=50total run time: 7915 s -> 440 sImproved
replace baseline MPC protocol [BH08] with COPML (Case 2, equal privacy)secure logistic regression training · CIFAR-10, N=50total run time: 7915 s -> 916 sImproved
replace sigmoid and no quantization with degree-1 polynomial sigmoid and quantized finite-field traininglogistic regression · CIFAR-10, 50 iterationstest accuracy: 81.75% -> 80.45%Hurt
replace sigmoid and no quantization with degree-1 polynomial sigmoid and quantized finite-field traininglogistic regression · GISETTE, 50 iterationstest accuracy: 97.5% -> 97.5%No clear effect
shift resources from parallelization to privacy (Case 1 to Case 2)COPML · CIFAR-10, N=50total run time: 440 s -> 916 sHurt

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy