AI Paper Atlas

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

Privacy-Preserving Face Recognition with Learnable Privacy Budgets in Frequency Domain

Jiazhen Ji, Huan Wang, Yuge Huang, Jiaxiang Wu, Xingkun Xu, Shouhong Ding, ShengChuan Zhang, Liujuan Cao, Rongrong Ji

ECCV 2022 · Federated learning and privacy › Privacy attacks and secure learning · approach: Visual privacy and face de-identification · 60 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
add frequency-domain transformation before noise (ablation)DP face recognition · LFWaccuracy: 84.78 -> 99.48Improved
add frequency-domain transformation before noise (ablation)DP face recognition · CFP-FPaccuracy: 63.87 -> 97.20Improved
add learnable privacy budgets instead of uniform budget (ablation)DP face recognition · LFWaccuracy: 65.966 -> 99.48Improved
remove DC component (ablation)BDCT baseline · LFW (no noise)accuracy: 99.68 -> 99.48No clear effect
remove DC component (ablation)BDCT baseline · CFP-FP (no noise)accuracy: 98.3 -> 98.39No clear effect
remove DC component (ablation)DP face recognition · IDCT visualization at budget 20face information leakageImproved
apply method instead of PEEPprivacy-preserving face recognition · CFP-FPaccuracy: 74.47 -> 97.20Improved
apply method instead of InstaHideprivacy-preserving face recognition · IJB-CTAR@FAR=1e-4: 69.02 -> 91.22Improved
apply method instead of Cloakprivacy-preserving face recognition · IJB-CTAR@FAR=1e-4: 33.82 -> 91.22Improved
train on privacy-preserved VGGFace2 instead of originalArcFace · LFWaccuracy: 99.60 -> 99.68No clear effect
train on privacy-preserved MS1M (budgets learned on VGGFace2)ArcFace · CFP-FPaccuracy: 97.94 -> 96.94Hurt
lower the privacy budget (ablation)DP face recognition · several face benchmarksaccuracy lossHurt

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