Submit

Login Login

Register Register

Home / Journals / CMC / Online First / doi:10.32604/cmc.2026.082629
Journal Menu
Special Issues
Table of Content

All issues

Online First

2026

2025

2024

2023

2022

2021

2020

2019

2018

2017

2016

2015

2014

2013

2012

2011

2010

2009

2008

2007

2006

2005

2004

Open Access

ARTICLE

Enhancing the Transferability of Adversarial Samples through Frequency-Domain Attenuation

Li Peng1,2, Xiangbing Li1,2, Kun Zou1, Yong Liu1,2,*, Haibo Huang1
1 School of Artificial Intelligence, Hubei University of Automotive Technology, Shiyan, China
2 Shiyan Key Laboratory of Electromagnetic Induction and Energy-Saving Technology, Hubei University of Automotive Technology, Shiyan, China
* Corresponding Author: Yong Liu. Email: email
(This article belongs to the Special Issue: Deep Learning for Next-Generation Cybersecurity: Architectures, Robustness and Applications)

Computers, Materials & Continua https://doi.org/10.32604/cmc.2026.082629

Received 19 March 2026; Accepted 15 May 2026; Published online 11 June 2026

Abstract

In recent years, the transferability of adversarial examples has attracted significant attention. To improve the effectiveness of black-box attacks, a frequency-domain decay constraint is introduced, inspired by weight decay and regularization techniques commonly employed during model training. By treating adversarial perturbations as inputs in an optimization process, this constraint aims to mitigate the excessive reliance on low-frequency components during adversarial example generation, thereby enhancing transferability. Fourier heatmaps are utilized to analyze the sensitivity of input samples, enabling a decomposition of the frequency spectrum into low-frequency and high-frequency components. Based on this analysis, low-frequency attenuation is applied in the Fourier domain to suppress dominant low-frequency information, followed by reconstruction of the perturbed inputs. The proposed frequency-domain attenuation strategy enjoys good compatibility with existing algorithms, and increases the attack success rate by approximately 1.53%–8.68% relative to the original method. Extensive experimental results show that the proposed method surpasses existing iterative attack methods and generates more transferable adversarial examples, demonstrating its effectiveness and superiority.

Keywords

Adversarial transferability; black-box attack; adversarial examples; frequency domain attenuation

  • 6

    View

  • 1

    Download

  • 0

    Like

Related articles
Copyright© 2026 Tech Science Press
© 1997-2026 TSP (Henderson, USA) unless otherwise stated

Share Link