Submit

Login Login

Register Register

Home / Journals / CMC / Online First / doi:10.32604/cmc.2025.071008
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

CASBA: Capability-Adaptive Shadow Backdoor Attack against Federated Learning

Hongwei Wu*, Guojian Li, Hanyun Zhang, Zi Ye, Chao Ma
School of Computer Science and Technology, Harbin University of Science and Technology, Harbin, 150080, China
* Corresponding Author: Hongwei Wu. Email: email

Computers, Materials & Continua https://doi.org/10.32604/cmc.2025.071008

Received 29 July 2025; Accepted 26 September 2025; Published online 08 December 2025

Abstract

Federated Learning (FL) protects data privacy through a distributed training mechanism, yet its decentralized nature also introduces new security vulnerabilities. Backdoor attacks inject malicious triggers into the global model through compromised updates, posing significant threats to model integrity and becoming a key focus in FL security. Existing backdoor attack methods typically embed triggers directly into original images and consider only data heterogeneity, resulting in limited stealth and adaptability. To address the heterogeneity of malicious client devices, this paper proposes a novel backdoor attack method named Capability-Adaptive Shadow Backdoor Attack (CASBA). By incorporating measurements of clients’ computational and communication capabilities, CASBA employs a dynamic hierarchical attack strategy that adaptively aligns attack intensity with available resources. Furthermore, an improved deep convolutional generative adversarial network (DCGAN) is integrated into the attack pipeline to embed triggers without modifying original data, significantly enhancing stealthiness. Comparative experiments with Shadow Backdoor Attack (SBA) across multiple scenarios demonstrate that CASBA dynamically adjusts resource consumption based on device capabilities, reducing average memory usage per iteration by 5.8%. CASBA improves resource efficiency while keeping the drop in attack success rate within 3%. Additionally, the effectiveness of CASBA against three robust FL algorithms is also validated.

Keywords

Federated learning; backdoor attack; generative adversarial network; adaptive attack strategy; distributed machine learning

  • 240

    View

  • 41

    Download

  • 0

    Like

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

Share Link