AI Paper Atlas

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

SemanticAdv: Generating Adversarial Examples via Attribute-conditioned Image Editing

Haonan Qiu, Chaowei Xiao, Lei Yang, Xinchen Yan, Honglak Lee, Bo Li

ECCV 2020 · Adversarial robustness and security › Attacks on text and graphs · approach: Adversarial perturbations beyond images · 163 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-space interpolation (at f0) instead of attribute-space interpolation (ablation)SemanticAdv · Face verification R-101-S, G-FPR=T-FPR=1e-3attack success rate (%): 0.08 -> 100.00Improved
interpolate on f0 rather than f-2 (ablation)SemanticAdv · R-101-S, G-FPR=T-FPR=1e-4attack success rate (%): 59.53 -> 99.45Improved
interpolate on f0 rather than f2 (ablation)SemanticAdv · R-101-S, G-FPR=T-FPR=1e-4attack success rate (%): 73.52 -> 99.45Improved
interpolate on f0 rather than f1 (ablation)SemanticAdv · R-101-S, G-FPR=T-FPR=1e-4attack success rate (%): 97.58 -> 99.45Improved
interpolate on f0 rather than f-1 (ablation)SemanticAdv · R-101-S, G-FPR=T-FPR=1e-3attack success rate (%): 100.00 -> 100.00No clear effect
use SemanticAdv instead of CW as the attackerFace++ black-box API · Face++ (T-FPR=1e-3)attack success rate (%): 37.24 -> 67.69Improved
use SemanticAdv instead of M-DI2-FGSMFace++ black-box API · Face++ (T-FPR=1e-4)attack success rate (%): 33.67 -> 48.21Improved
use SemanticAdv instead of M-DI2-FGSMAliYun black-box API · AliYun (T-FPR=1e-4)attack success rate (%): 18.00 -> 19.50Improved
add attribute-conditioned editing before CW (StarGAN+CW)CW · AliYun (T-FPR=1e-4)attack success rate (%): 9.50 -> 8.50Hurt
add attribute-conditioned editing before CW (StarGAN+CW)CW · Face++ (T-FPR=1e-3)attack success rate (%): 37.24 -> 47.45Improved
generate adversarial examples with SemanticAdv instead of PGD against adversarial trainingadversarial-training defense · Adversarial-training defensedefense accuracy (%): 46.7 -> 10Improved
use SemanticAdv instead of CW on AMT perceptual realismSemanticAdv · AMT user study, G-FPR<1e-4fraction judged reasonably-looking (%): 30.27 -> 39.14Improved

Later papers that compared with this method

1 later accepted paper reports SemanticAdv as a baseline in their results tables; 1 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