AI Paper Atlas

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

SMP-Attack: Boosting the Transferability of Feature Importance-based Adversarial Attack with Semantics-aware Multi-granularity Patchout

Wen Yang, Guodong Liu, Di Ming

ICCV 2025 · Adversarial robustness and security › Black-box and transfer attacks · approach: Transfer attacks on face recognition · 3 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 SMP-Attack instead of MFAAfeature importance attack · 6 undefended CNNs, 3 surrogates avgattack success rate (%): 92.03% outperforming MFAA by 3.77%Improved
combine SMP with PIM and DIM instead of MFAAPIDI attacks · 6 undefended CNNsattack success rate (%): 93.93%, surpassing PIDI-MFAA by 1.07%Improved
use SMP-Attack instead of MFAAfeature importance attack · 4 defended CNNsattack success rate (%): 3.93% improvement over MFAAImproved
combine SMP with PIM and DIM instead of MFAAPIDI attacks · 4 defended CNNsattack success rate (%): 1.60% compared to PIDI-MFAAImproved
use SMP-Attack instead of MFAAfeature importance attack · 4 ViTsattack success rate (%): approximately 6.47% compared to MFAAImproved
combine SMP with PIM and DIM instead of MFAAPIDI attacks · 4 ViTsattack success rate (%): increase of 5.47% over PIDI-MFAAImproved
add multi-granularity (vary both d and c) instead of single granularity (ablation)SMP patchout · ImageNet-compatible black-boxattack success rate (%)Improved
add multi-stage training instead of joint or alternating single-stage multi-layer training (ablation)SMP-Attack · ImageNet-compatible black-boxattack success rate (%)Improved
use large irregular patches D=[3,4,5] with CSharp in the intermediate layer (ablation)single-stage SMP · Vgg-16 surrogate, Inc-v3/IncRes-v2ens/Swin-Battack success rate (%)Improved
use small regular patches D=[1,2,3] with CSmooth in the shallow layer (ablation)multi-stage SMP · Vgg-16 surrogate, Inc-v3/IncRes-v2ens/Swin-Battack success rate (%)Improved
set modify probability pm between 0.2 and 0.3 (ablation)SMP-Attack · Res152-v1 surrogate, Vgg-16/Inc-v3ens3/PiT-Sattack success rate (%)Improved
set ensemble number M to 60 (ablation)SMP-Attack · Res152-v1 surrogate, Vgg-16/Inc-v3ens3/PiT-Sattack success rate (%)Improved

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