AI Paper Atlas

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

OPOM: Customized Invisible Cloak Towards Face Privacy Protection

Yaoyao Zhong, Weihong Deng

TPAMI 2022 · Federated learning and privacy › Privacy attacks and secure learning · approach: Visual privacy and face de-identification · 39 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
model identity subspace as convex hull instead of a single point (ablation)FI-UAP · Privacy-Commons, Softmax source, ArcFace target (Top-1)Top-1 protection success rate (%): 72.3 -> 78.0Improved
use convex hull instead of affine hull for the identity subspace (ablation)OPOM · Privacy-Commons, Softmax source, ArcFace target (Top-1)Top-1 protection success rate (%): 73.0 -> 78.0Improved
use convex hull instead of class center (ablation)OPOM · Privacy-Commons, Softmax source, ArcFace target (Top-1)Top-1 protection success rate (%): 76.9 -> 78.0Improved
add intra-class interactions (cross-image gradients) to FI-UAP (ablation)FI-UAP · Privacy-Commons, Softmax source, ArcFace target (Top-1)Top-1 protection success rate (%): 72.3 -> 76.9Improved
use class center versus FI-UAP+ intra-class formulation (ablation)OPOM-ClassCenter · Privacy-Commons, Softmax source, ArcFace target (Top-1)Top-1 protection success rate (%): 76.9 -> 76.9No clear effect
aggregate all training images into one universal mask instead of per-identity mask (ablation)FI-UAP · Privacy-Commons, Softmax source, ArcFace target (Top-1)Top-1 protection success rate (%): 72.3 -> 53.4Hurt
use convex hull instead of single-point FI-UAP (ablation)OPOM · Privacy-Commons, CosFace source, MobileNet target (Top-1)Top-1 protection success rate (%): 55.6 -> 62.3Improved
use convex hull instead of affine hull (ablation)OPOM · Privacy-Commons, CosFace source, MobileNet target (Top-1)Top-1 protection success rate (%): 58.6 -> 62.3Improved
use convex hull instead of single-point FI-UAP (ablation)OPOM · Privacy-Celebrities, Softmax source, ArcFace target (Top-1)Top-1 protection success rate (%): 56.5 -> 63.8Improved
use convex hull instead of single-point FI-UAP (ablation)OPOM · Privacy-Celebrities, ArcFace source, SENet target (Top-1)Top-1 protection success rate (%): 54.3 -> 62.3Improved
add momentum boosting and DFANet transferability methodsOPOM-ConvexHull · Privacy-Commons, Softmax source, ArcFace target (Top-1)Top-1 protection success rate (%): 78.0 -> 81.2Improved

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