AI Paper Atlas

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

Personalized and Invertible Face De-Identification by Disentangled Identity Information Manipulation

Jingyi Cao, Bo Liu, Yunqian Wen, Rong Xie, Li Song

ICCV 2021 · Federated learning and privacy › Privacy attacks and secure learning · approach: Visual privacy and face de-identification · 90 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
use ours instead of Gu et al.face de-identification · FaceNet (CASIA)successful protection rate: 0.704 -> 0.913Improved
use ours instead of Gu et al.face de-identification · FaceNet (VGGFace2)successful protection rate: 0.695 -> 0.928Improved
use ours instead of Gu et al.face de-identification · Face Recognition libraryidentity distance: 0.82234 -> 0.79195Hurt
use ours instead of DeepPrivacyface de-identification · FaceNet (VGGFace2)successful protection rate: 0.816 -> 0.928Improved
use ours instead of DeepPrivacyface de-identification · CelebA-HQ face regionpixel distance: 5.005 -> 0.225Improved
use ours instead of DeepPrivacyface de-identification · CelebA-HQface detectability: 1.0 -> 0.9973No clear effect
use ours instead of Gu et al.face de-identification · CelebA-HQface detectability: 0.8585 -> 0.9973Improved
restore with the correct password instead of a wrong oneface recovery · Face Recognition librarysuccessful protection rate: 0.904 -> 0.035Improved
restore with the correct password instead of a wrong oneface recovery · Face Recognition libraryidentity distance: 0.794 -> 0.228Improved
use ours instead of Gu et al. for restorationface recovery · Restored image qualityLPIPS: 0.186 -> 0.062Improved
use ours instead of Gu et al. for restorationface recovery · Restored image qualitySSIM: 0.827 -> 0.902Improved
use ours instead of Gu et al. for restorationface recovery · Restored image qualityPSNR: 27.602 -> 27.501Hurt

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