AI Paper Atlas

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

Password-conditioned Anonymization and Deanonymization with Face Identity Transformers

Xiuye Gu, Weixin Luo, Michael S. Ryoo, Yong Jae Lee

ECCV 2020 · Federated learning and privacy › Privacy attacks and secure learning · approach: Visual privacy and face de-identification · 73 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 feature dissimilarity loss L_dis (ablation)face identity transformer · CASIAidentity multimodality (qualitative)Improved
add explicit wrong-reconstruction training (WR) (ablation)face identity transformer · CASIAidentity concealment under wrong password (qualitative)Improved
add auxiliary password-predicting network Q with L_aux (ablation)face identity transformer · CASIAphoto-realism and multimodality (qualitative)Improved
add face classification loss on reconstruction L_rec_cls (ablation)face identity transformer · CASIAreconstruction quality (qualitative)Improved
use adversarial face classification training instead of fixed non-adversarial classifier loss (ablation)face identity transformer · CASIAphoto-realism (qualitative)Improved
train identity change and recovery jointly end-to-end instead of separate deanonymizers for baselines (ablation)face identity transformer · CASIALPIPS reconstruction error: 0.08 -> 0.03Improved
use face identity transformer instead of Blur baselineface identity transformer · CASIALPIPS reconstruction error: 0.30 -> 0.03Improved
use face identity transformer instead of Ren et alface identity transformer · LFWL1 reconstruction error (LFW): 0.06 -> 0.04Improved
use wrong-password recovery instead of anonymization alone to hide identityface identity transformer · CASIA AMTpercent judged same as input: 4.7 -> 0.7Improved
use 4 bits chunked N/4 16-way classifiers for 16-bit password in Qface identity transformer · CASIAclassifier designNo clear effect

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