AI Paper Atlas

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

[Re] Privacy-preserving collaborative learning with automatic transformation search

Alfonso Taboada Warmerdam, Lodewijk Loerakker, Lucas Meijer, Ole Nissen

NeurIPS 2022 · Federated learning and privacy › Privacy attacks and secure learning · approach: Encryption-based private learning

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
apply the hybrid of searched transformation policies instead of no transformationResNet20 · CIFAR100, Adam+Cosine reconstruction attackPSNR: 13.88 -> 7.64Improved
apply the hybrid of searched transformation policies instead of no transformationResNet20 · CIFAR100ACC: 76.88 -> 77.92Improved
apply the hybrid of searched transformation policies instead of no transformationConvNet · CIFAR100, Adam+Cosine reconstruction attackPSNR: 13.07 -> 6.83Improved
apply the hybrid of searched transformation policies instead of no transformationConvNet · CIFAR100ACC: 70.13 -> 70.27Improved
apply the hybrid of searched transformation policies instead of no transformationResNet20 · F-MNIST, Adam+Cosine reconstruction attackPSNR: 10.04 -> 7.60Improved
apply the hybrid of searched transformation policies instead of no transformationResNet20 · F-MNISTACC: 95.03 -> 92.23Hurt
apply the hybrid of searched transformation policies instead of no transformationConvNet · F-MNIST, Adam+Cosine reconstruction attackPSNR: 9.12 -> 6.94Improved
apply the hybrid of searched transformation policies instead of no transformationConvNet · F-MNISTACC: 94.25 -> 91.35Hurt
use hybrid selection rather than one fixed searched policy (ablation)ResNet20 · CIFAR100ACC: 70.56 -> 77.92Improved
use hybrid selection rather than one fixed searched policy (ablation)ConvNet · CIFAR100ACC: 66.98 -> 70.27Improved
use hybrid selection rather than one fixed searched policy (ablation)ResNet20 · F-MNISTACC: 89.41 -> 92.23Improved
use hybrid selection rather than one fixed searched policy (ablation)ConvNet · F-MNISTACC: 90.56 -> 91.35Improved

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