AI Paper Atlas

Research map / Adversarial robustness and security / Black-box and transfer attacks

Boosting Adversarial Transferability via Gradient Relevance Attack

Hegui Zhu, Yuchen Ren, Xiaoyan Sui, Lianping Yang, Wuming Jiang

ICCV 2023 · Adversarial robustness and security › Black-box and transfer attacks · approach: Transferable adversarial examples · 77 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 gradient relevance framework and decay indicator to MI-FGSM (GRA) versus AdmixInc-v3 source · ILSVRC 2012 val 1k, 7 targets averageattack success rate (%): 62.3 -> 72.6Improved
use average gradient relevance (GRA) instead of individual relevance (I-GRA) (ablation)GRA · Inc-v3 source, 7 targets averageattack success rate (%): 71.7 -> 72.6Improved
combine GRA with combined transformation (DI, TI, SI)GRA · Inc-v3 source, 7 targets averageattack success rate (%): 72.6 -> 90.4Improved
apply GRA in an ensemble attack versus Admix on defended modelsGRA · nine defended modelsattack success rate (%): at least +12.3% over other attacks; 83.0% averageImproved
apply GRA on online modelsGRA ensemble · Tencent Cloud and Baidu AI Cloudattack success rate (%): +11.1% over VTNI, +11.4% over AdmixImproved
increase sample quantity m (ablation)GRA · Inc-v3 sourceattack success rate (%)Improved
use GRA with m=5 versus VTNI with m=20 (ablation)GRA · Inc-v4 and IncRes-v2ens targetsattack success rate (%): 78.1 vs 76.5 (Inc-v4); 24.8 vs 18.8 (IncRes-v2ens)Improved
enlarge sample range factor beta to 3.5 (ablation)GRA · Inc-v3 source, 7 targetsattack success rate (%)Improved
set attenuation factor eta near 0.94 (ablation)GRA decay indicator · Inc-v3 source, normal and adversarial groupsaverage attack success rate (%)Improved
GRA versus Admix on IncRes-v2 white-box and IncRes-v2 source normal targetsGRA · IncRes-v2 source, normally trained targetsattack success rate (%): Inc-v3 89.9 (Admix) vs 86.0 (GRA)Mixed

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

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