AI Paper Atlas

Research map / Adversarial robustness and security / Certified and empirical robustness

Towards Certifiably Robust Face Recognition

Seunghun Paik, Dongsoo Kim, Chanwoo Hwang, Sunpill Kim, Jae Hong Seo

ECCV 2024 · Adversarial robustness and security › Certified and empirical robustness · approach: Neural network robustness verification · 2 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-norm regularization loss (xi=3) to a 1-Lipschitz face recognition model (ablation)1-Lipschitz FR model (SLL + ElasticFace) · LFW untargeted certification eps=1.5CRA_U (%): 0 -> 100Improved
increase regularization strength xi from 0 to 5 (ablation)1-Lipschitz FR model · LFWTAR@FAR=1e-3 (%): 97.73 -> 65.27Hurt
increase regularization strength xi from 0 to 5 (ablation)1-Lipschitz FR model · LFW impersonation certification eps=0.75CRA_I (%): 0 -> 93.95Improved
add feature-norm regularization (xi=3) vs xi=0 for empirical robustness (ablation)1-Lipschitz FR model · LFW untargeted PGD20 eps=3.0ERA_U (%): 0.18 -> 100Improved
increase xi from 0 to 5 for dodging certification at eps=0.25 (ablation)1-Lipschitz FR model · LFW dodging certification eps=0.25CRA_D (%): 0 -> 46.68 (xi=1) -> 66.82 (xi=3) -> 53.06 (xi=5)Mixed
use certified 1-Lipschitz model instead of non-robust ArcFace/ElasticFace/AdaCosFace recognition · LFW untargeted PGD20 eps=3.0ERA_U (%): 0.22 -> 100 (vs ArcFace)Improved
use certified 1-Lipschitz model on small-eps dodging attackFace recognition · LFW dodging PGD20 eps=0.25ERA_D (%): 98.03 (ArcFace) vs 74.22 (Ours)Hurt
use 1-Lipschitz backbone instead of non-robust backboneFace recognition · LFWTAR@FAR=1e-3 (%): 99.75 (ArcFace) vs 83.97 (Ours)Hurt
use classification-style header (LLN plus margin) instead of ElasticFace for 1-Lipschitz FR (ablation)1-Lipschitz FR model · Face recognition trainingaccuracyHurt
compare with adversarially trained FR models (PGD-AT, TRADES)Face recognition · LFWTAR@FAR=1e-3 (%): 28.47-67.17 vs 83.97 (ours)Hurt

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