AI Paper Atlas

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

SensitiveNets: Learning Agnostic Representations with Application to Face Images

Aythami Morales, Julián Fiérrez, Rubén Vera-Rodríguez, Rubén Tolosana

TPAMI 2020 · Federated learning and privacy › Privacy attacks and secure learning · approach: Visual privacy and face de-identification · 197 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
apply SensitiveNets projection to embeddingsResNet-50 face embeddings · LFW verificationaccuracy: 98.4% -> 95.8%Hurt
apply SensitiveNets projectionResNet-50 embeddings · DiveFace gender (NN)accuracy: 97.7% -> 58.8%Improved
apply SensitiveNets projectionResNet-50 embeddings · DiveFace ethnicity (NN)accuracy: 98.8% -> 55.1%Improved
apply SensitiveNets projectionResNet-50 embeddings · DiveFace gender (SVM)accuracy: 96.2% -> 56.3%Improved
apply SensitiveNets projectionResNet-50 embeddings · DiveFace gender (RF)accuracy: 95.1% -> 54.6%Improved
apply SensitiveNets projectionResNet-50 embeddings · DiveFace ethnicity (SVM)accuracy: 98.2% -> 54.1%Improved
apply SensitiveNets projectionResNet-50 embeddings · DiveFace ethnicity (RF)accuracy: 97.3% -> 53.5%Improved
obfuscate gender at image level with differential privacyResNet-50 embeddings · CelebA gender (SVM)accuracy: 98.4% -> 98.3%No clear effect
apply SensitiveNets rather than image-level obfuscationResNet-50 embeddings · CelebA gender (SVM)accuracy: 98.4% -> 67.3%Improved
train SVM on SensitiveNets representationSVM on embeddings · CelebA Attractivenessequal opportunity gap: 30.1 -> 6.8Improved
train SVM on SensitiveNets representationSVM on embeddings · CelebA Smilingequal opportunity gap: 14.5 -> 6.0Improved
train SVM on SensitiveNets representationSVM on embeddings · CelebA Attractivenessaccuracy: 74.3 -> 77.7Improved

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