AI Paper Atlas

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

Using LIP to Gloss Over Faces in Single-Stage Face Detection Networks

Siqi Yang, Arnold Wiliem, Shaokang Chen, Brian C. Lovell

ECCV 2018 · Adversarial robustness and security › Attacks on text and graphs · approach: Defenses against universal perturbations · 4 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
replace whole-image perturbation (IMP) with ERF-cropped localized perturbation (LP)I-FGSM · FDDBattack success rate (%): 53.9 -> 94.9Improved
replace IMP with LIP-HI-FGSM · FDDBattack success rate (%): 53.9 -> 93.8Improved
compute perturbation per instance before cropping (LIP-H) instead of jointly (LP) (ablation)I-FGSM · FDDBattack success rate (%): 94.9 -> 93.8No clear effect
compute perturbation per instance before cropping (LIP-H) instead of jointly (LP) (ablation)I-FGSM · WIDER FACE val (easy)attack success rate (%): 67.4 -> 71.3Improved
compute perturbation per instance before cropping (LIP-H) instead of jointly (LP) (ablation)I-FGSM · WIDER FACE val (medium)attack success rate (%): 61.7 -> 65.7Improved
compute perturbation per instance before cropping (LIP-A) instead of jointly (LP) (ablation)I-FGSM · WIDER FACE val (hard)attack success rate (%): 62.1 -> 69.5Improved
replace IMP with LIP-ADeepFool · WIDER FACE val (hard)attack success rate (%): 39.6 -> 66.6Improved
replace IMP with LIP-ADeepFool · WIDER FACE val (easy)attack success rate (%): 45.3 -> 53.2Improved
attack highest-confidence proposal only (LIP-H) instead of all proposals (LIP-A) (ablation)LIP · WIDER FACE val (easy)attack success rate (%): 69.5 -> 71.3No clear effect
attack highest-confidence proposal only (LIP-H) instead of all proposals (LIP-A) (ablation)LIP · WIDER FACE val (hard)attack success rate (%): 69.5 -> 65.6Hurt
increase number of faces from 1 to 81 at distance 40IMP(I-FGSM) · Synthetic facesattack success rate (%): 100 -> 18.3Hurt
increase distance between faces from 40 to 160 (16 faces)IMP(I-FGSM) · Synthetic facesattack success rate (%): 34 -> 38.9Improved

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