Submit

Login Login

Register Register

Home / Journals / CMC / Online First / doi:10.32604/cmc.2026.081490
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

Adversarial Example Transfer Method for Vision-Language Pre-Training Models Based on Negative Sample Feature Perturbation

Zhichao Pei, Ou Ye*, Panyu Yang, Kaiwen He
College of Artificial Intelligence & Computer Science, Xi’an University of Science and Technology, Xi’an, China
* Corresponding Author: Ou Ye. Email: email

Computers, Materials & Continua https://doi.org/10.32604/cmc.2026.081490

Received 03 March 2026; Accepted 17 April 2026; Published online 12 May 2026

Abstract

To address the issue of insufficient transferability of existing adversarial example generation methods for vision-language pre-training (VLP) models, this paper proposes an adversarial example transfer method for VLP models based on negative sample feature perturbation. First, a novel cross-modal collaborative perturbation strategy is constructed. By introducing negative samples into the cross-modal perturbation mechanism, the strategy explores more perturbation directions, breaks the original modal alignment constraints and avoids the local focus of adversarial perturbations. Then, to reduce the computational cost, a dynamic threshold attack strategy is built to measure the modal similarity of the generated adversarial examples. Finally, with the help of a multi-modal fusion encoder, a cross-modal fusion semantic attack (CFSA) module is designed. This module extracts the middle-layer features of image-text pairs and improves the transfer attack effect of adversarial examples. The proposed attack method is experimentally evaluated on the Flickr30K and MSCOCO datasets. The results show that for the adversarial examples generated on the Flickr30K dataset, the attack success rate (ASR) of the proposed method reaches up to 95.3% on multiple black-box models; for those generated on the MSCOCO dataset, the maximum attack success rate on multiple black-box models reaches 70.17%. Compared with the current methods, the adversarial examples generated by the proposed method achieve better attack performance.

Keywords

Vision-language pre-training model; multimodal; adversarial attack transferability; cross-modality perturbation; negative samples

  • 129

    View

  • 21

    Download

  • 2

    Like

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

Share Link