AI Paper Atlas

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

AdvFM: Lookahead Flow-Matching Velocity-Field Attacks for Imperceptible and Transferable Adversarial Examples

Runze Liu, Zeyue Wang, Fanghui Sun, Rui Liu, Yihan Yan, Shen Wang, Zhaoyang Zhang

CVPR 2026 · Adversarial robustness and security › Black-box and transfer attacks · approach: Transfer attacks on face recognition

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 lookahead two-point loss (ablation)AdvFM · ImageNet black-box avg (ResNet50)ASR (%): 64.31 -> 72.05Improved
add lookahead two-point loss (ablation)AdvFM · ImageNet white-box (ResNet50)ASR (%): 91.72 -> 94.45Improved
attack flow-matching velocity field instead of diffusion denoise/renoiseDiffAttack/APA · ImageNet VGG19 sourceaverage black-box ASR (%): 65.86 (APA) -> 70.35Improved
attack flow-matching velocity field instead of diffusionAPA · ImageNet ViT-B/16 sourceaverage black-box ASR (%): 69.73 -> 68.22Hurt
use AdvFM against purification NRPAPA · NRP defenseASR (%): 81.20 -> 94.98Improved
use AdvFM against DiffPureAPA · DiffPure defenseASR (%): 63.30 -> 61.33No clear effect
use AdvFM against adversarially trained ViTsAdvAD · RAT ViT-B/16ASR (%): 97.70 -> 98.53Improved
use AdvFM on adversarially trained ResNetsDiffAttack · Madry RN50ASR (%): 83.84 -> 81.89No clear effect

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 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