Submit

Login Login

Register Register

Home / Journals / CMC / Online First / doi:10.32604/cmc.2025.072449
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

AdvYOLO: An Improved Cross-Conv-Block Feature Fusion-Based YOLO Network for Transferable Adversarial Attacks on ORSIs Object Detection

Leyu Dai1,2,3, Jindong Wang1,2,3, Ming Zhou1,2,3, Song Guo1,2,3, Hengwei Zhang1,2,3,*
1 School of Cryptography Engineering, Information Engineering University, Zhengzhou, 450000, China
2 State Key Laboratory of Mathematical Engineering and Advanced Computing, Zhengzhou, 450001, China
3 Henan Key Laboratory of Information Security, Zhengzhou, 450001, China
* Corresponding Author: Hengwei Zhang. Email: email
(This article belongs to the Special Issue: Advances in Object Detection: Methods and Applications)

Computers, Materials & Continua https://doi.org/10.32604/cmc.2025.072449

Received 27 August 2025; Accepted 05 November 2025; Published online 12 December 2025

Abstract

In recent years, with the rapid advancement of artificial intelligence, object detection algorithms have made significant strides in accuracy and computational efficiency. Notably, research and applications of Anchor-Free models have opened new avenues for real-time target detection in optical remote sensing images (ORSIs). However, in the realm of adversarial attacks, developing adversarial techniques tailored to Anchor-Free models remains challenging. Adversarial examples generated based on Anchor-Based models often exhibit poor transferability to these new model architectures. Furthermore, the growing diversity of Anchor-Free models poses additional hurdles to achieving robust transferability of adversarial attacks. This study presents an improved cross-conv-block feature fusion You Only Look Once (YOLO) architecture, meticulously engineered to facilitate the extraction of more comprehensive semantic features during the backpropagation process. To address the asymmetry between densely distributed objects in ORSIs and the corresponding detector outputs, a novel dense bounding box attack strategy is proposed. This approach leverages dense target bounding boxes loss in the calculation of adversarial loss functions. Furthermore, by integrating translation-invariant (TI) and momentum-iteration (MI) adversarial methodologies, the proposed framework significantly improves the transferability of adversarial attacks. Experimental results demonstrate that our method achieves superior adversarial attack performance, with adversarial transferability rates (ATR) of 67.53% on the NWPU VHR-10 dataset and 90.71% on the HRSC2016 dataset. Compared to ensemble adversarial attack and cascaded adversarial attack approaches, our method generates adversarial examples in an average of 0.64 s, representing an approximately 14.5% improvement in efficiency under equivalent conditions.

Keywords

Remote sensing; object detection; transferable adversarial attack; feature fusion; cross-conv-block

  • 302

    View

  • 52

    Download

  • 0

    Like

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

Share Link