AI Paper Atlas

Research map / Image generation / Editing and style transfer

CLIP2Protect: Protecting Facial Privacy Using Text-Guided Makeup via Adversarial Latent Search

Fahad Shamshad, Muzammal Naseer, Karthik Nandakumar

CVPR 2023 · Image generation › Editing and style transfer · approach: Identity-preserving face manipulation · 49 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 latent-manifold search with text-guided makeup and identity-preserving regularization instead of AMT-GANBlack-box face verification impersonation · CelebA-HQ and LADN-DatasetPSR (%): 52.84 -> 64.90Improved
Use CLIP2Protect instead of TIP-IMFace identification dodging · LFWRank-1-U PSR: 77.8 -> 82.2Improved
Use CLIP2Protect instead of TIP-IMFace identification dodging · LFWRank-5-U PSR: 54.9 -> 58.5Improved
Use CLIP2Protect instead of TIP-IMFace identification impersonation · LFWRank-1-T PSR: 19.7 -> 23.4Improved
Use CLIP2Protect instead of TIP-IMFace identification impersonation · LFWRank-5-T PSR: 41.9 -> 51.05Improved
Add identity-preserving latent regularization (ablation)CLIP2Protect · Latent-loss ablationFID: 43.2 -> 27.8Improved
Add identity-preserving latent regularization (ablation)CLIP2Protect · Latent-loss ablationPSR (%): 93.6 -> 76.2Hurt
Decrease latent-loss weight from 0.5 to 0.0001 (ablation)CLIP2Protect · Latent-loss ablationPSR (%): 31.2 -> 90.0Improved
Decrease latent-loss weight from 0.5 to 0.0001 (ablation)CLIP2Protect · Latent-loss ablationFID: 11.6 -> 38.4Hurt
Add makeup text guidance (ablation)CLIP2Protect · Face verification impersonationvisual naturalnessImproved
Restrict adversarial optimization to identity-preserving latent codes (ablation)CLIP2Protect · Face protectionhuman-perceived identity preservationImproved
Vary the makeup prompt across five styles (ablation)CLIP2Protect · CelebA-HQPSR: 74.1, 77.3, 78.4, 78.7, 79.2; Std. 1.24No clear effect

Later papers that compared with this method

2 later accepted papers report CLIP2Protect as a baseline in their results tables; 2 of them report a better number on most of the results they share with it.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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