EUVIMEDOpdag EUVIMED
Crossref

Secure Collaborative Learning for Self-Adaptive Systems on Connected Autonomous Vehicles

Xiaotong Wu, Yuwen Liu, Xiaoxiao Chi, Rong Jiang, Xiaokang Zhou, Wajid Rafique, Maqbool Khan

ACM Transactions on Autonomous and Adaptive Systems · 2025-09-30 · 20 (3) · 1-30

DOI: 10.1145/3690768 ↗

At a glance

Journal article in ACM Transactions on Autonomous and Adaptive Systems, published online on 2025-09-13. Written by Xiaotong Wu and 6 co-authors. Cited 8 times so far (Crossref); 72 references. Funded by: National Natural Science Foundation of China, Grants-in-Aid for Scientific Research (C) from Japan Society for the Promotion of Science.

AbstractBibliografiske oplysningerCiteRelated studies

Abstract (original language)

As an advanced carrier of on-board sensors, connected autonomous vehicle (CAV) can be viewed as an aggregation of self-adaptive systems with monitor-analyze-plan-execute (MAPE) for vehicle-related services. Meanwhile, machine learning (ML) has been applied to enhance analysis and plan functions of MAPE so that self-adaptive systems have optimal adaption to changing conditions. However, most of ML-based approaches don’t utilize CAVs’ connectivity to collaboratively generate an optimal learner for MAPE, because of sensor data threatened by gradient leakage attack (GLA). In this article, we first design an intelligent architecture for MAPE-based self-adaptive systems on web 3.0-based CAVs, in which a collaborative machine learner supports the capabilities of managing systems. Then, we observe by practical experiments that importance sampling of sparse vector technique (SVT) approaches cannot defend GLA well. Next, we propose a fine-grained SVT approach to secure the learner in MAPE-based self-adaptive systems that uses layer and gradient sampling to select uniform and important gradients. At last, extensive experiments show that our private learner spends a slight utility cost for MAPE (e.g., \(0.77\%\) decrease in accuracy) defending GLA and outperforms the typical SVT approaches in terms of defense (increased by \(10\) – \(14\%\) attack success rate) and utility (decreased by \(1.29\%\) accuracy loss).

Funding

  • National Natural Science Foundation of China
  • Grants-in-Aid for Scientific Research (C) from Japan Society for the Promotion of Science

Cite

APA

Wu, X., Liu, Y., Chi, X., Jiang, R., Zhou, X., Rafique, W., & Khan, M. (2025). Secure Collaborative Learning for Self-Adaptive Systems on Connected Autonomous Vehicles. ACM Transactions on Autonomous and Adaptive Systems, 20(3), 1-30. https://doi.org/10.1145/3690768

Vancouver

Wu X, Liu Y, Chi X, Jiang R, Zhou X, Rafique W, et al. Secure Collaborative Learning for Self-Adaptive Systems on Connected Autonomous Vehicles. ACM Transactions on Autonomous and Adaptive Systems. 2025;20(3):1-30. doi:10.1145/3690768

BibTeX
@article{Wu2025,
  author = {Wu, Xiaotong and Liu, Yuwen and Chi, Xiaoxiao and Jiang, Rong and Zhou, Xiaokang and Rafique, Wajid and Khan, Maqbool},
  title = {Secure Collaborative Learning for Self-Adaptive Systems on Connected Autonomous Vehicles},
  journal = {ACM Transactions on Autonomous and Adaptive Systems},
  year = {2025},
  volume = {20},
  number = {3},
  pages = {1--30},
  doi = {10.1145/3690768}
}
Start for free →