AI Paper Atlas

Research map / Adversarial robustness and security / Attacks on text and graphs

AdversariaLeak: External Information Leakage Attack Using Adversarial Samples on Face Recognition Systems

Roye Katzav, Amit Giloni, Edita Grolman, Hiroo Saito, Tomoyuki Shibata, Tsukasa Omino, Misaki Komatsu, Yoshikazu Hanatani, Yuval Elovici, Asaf Shabtai

ECCV 2024 · Adversarial robustness and security › Attacks on text and graphs · approach: Defenses against universal perturbations · 1 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 AdversariaLeak (unique adversarial samples) instead of loss test attackEIL attack on face verification · CelebA young and male propertiescorrect property inferenceImproved
use AdversariaLeak instead of threshold test attackEIL attack on face verification · CelebA 5 o'clock shadowcorrect property inferenceImproved
use AdversariaLeak instead of loss test attack on 5 o'clock shadowEIL attack on face verification · CelebA 5 o'clock shadowcorrect property inferenceNo clear effect
stricter scenario with different head architecture for target vs substituteLoss test attack · CelebAcorrect property inferenceHurt
fine-tune backbone rather than use pre-trained backboneAdversariaLeak · MAAD-Face vs CelebA, 50% distributionbias toward specific property valueImproved
use unique adversarial samples with small query budget (ablation)AdversariaLeak · CelebA and MAAD-Facecorrect property inference: 24 to 60 queriesImproved

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