AggMo-Enhanced Momentum Attack: A Plug-and-Play Framework for Boosting Adversarial Transferability
Applied Sciences · 08.05.2026 · 16 (10) · 4645
DOI: 10.3390/app16104645 ↗Kurz gefasst
Fachartikel in der Zeitschrift Applied Sciences, online erschienen am 08.05.2026. Verfasst von Qiaoyi Li und 3 weiteren Autor:innen. Die Arbeit nennt 44 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Abstract (Originalsprache)
Most adversarial attack methods achieve high success rates under the white-box setting. However, these methods often lack transferability when targeting other deep neural network (DNN) models. Momentum-based attacks have emerged as an effective strategy to enhance transferability by incorporating a momentum term to stabilize update directions. While simple constant-momentum methods (e.g., MI-FGSM) or advanced variants (e.g., NI-FGSM, VMI-FGSM) have shown promise, they either use a single momentum decay factor or introduce significant computational overhead. To address this, we propose a novel plug-and-play momentum aggregation framework named AggMo-Attack. Our key insight is that a single momentum term with a fixed decay factor cannot optimally capture the multi-scale temporal correlations in gradients during adversarial optimization. Inspired by the Aggregated Momentum (AggMo) optimizer, we designed a multi-momentum aggregation module that maintains and weightedly combines multiple velocity vectors with different decay factors. This framework can be seamlessly integrated into existing momentum-based attack methods (e.g., MI-FGSM, NI-FGSM, VMI-FGSM) as a drop-in replacement for their standard momentum update step. Extensive experiments demonstrate that integrating our AggMo module significantly improves adversarial transferability. Our work provides a versatile and effective tool for enhancing momentum-based adversarial attacks and opens a new direction for designing adaptive attack strategies.
Zitieren
APA
Li, Q., Wang, Z., Ran, C., & Shen, H. (2026). AggMo-Enhanced Momentum Attack: A Plug-and-Play Framework for Boosting Adversarial Transferability. Applied Sciences, 16(10), 4645. https://doi.org/10.3390/app16104645
Vancouver
Li Q, Wang Z, Ran C, Shen H. AggMo-Enhanced Momentum Attack: A Plug-and-Play Framework for Boosting Adversarial Transferability. Applied Sciences. 2026;16(10):4645. doi:10.3390/app16104645
BibTeX
@article{Li2026,
author = {Li, Qiaoyi and Wang, Zhengjie and Ran, Chengxiang and Shen, Haifeng},
title = {AggMo-Enhanced Momentum Attack: A Plug-and-Play Framework for Boosting Adversarial Transferability},
journal = {Applied Sciences},
year = {2026},
volume = {16},
number = {10},
pages = {4645},
doi = {10.3390/app16104645}
}
EUVIMED