Student or educator? Sign up with your school email and get 6 months of Pro free.

The DOI matches its Crossref record; 235 of the 238 references it cites were found in a registry or an index.

Advancing Intrusion Detection in V2X Networks: A Comprehensive Survey on Machine Learning, Federated Learning, and Edge AI for V2X Security

Abdel Hakeem, Shimaa A., Kim, HyungWon·2025·IEEE Transactions on Intelligent Transportation Systems

Abstract

The security of Vehicle-to-Everything (V2X) networks is fundamental to the realization of next-generation intelligent transportation systems. However, the dynamic nature of V2X environments introduces critical challenges in ensuring robust Intrusion Detection Systems (IDS), particularly concerning false alarm rates, adversarial attacks, computational complexity, and real-world deployment constraints. Traditional centralized machine learning-based IDS suffer from high computation costs, privacy risks, bandwidth constraints, and scalability limitations, making them impractical for real-time, distributed vehicular networks. To address these gaps, this paper provides a comprehensive and structured survey of IDS methodologies in V2X security, focusing on Federated Learning (FL) and Edge AI for privacy-preserving and scalable IDS solutions. Unlike prior works, we systematically analyze and benchmark intrusion detection datasets, highlighting limitations in detecting zero-day attacks and exploring the need for hybrid datasets that integrate real-world vehicular data with adversarial attack scenarios. Furthermore, we investigate the adversarial robustness of ML-based IDS, analyzing AI-based evasion techniques, data poisoning threats, and misbehavior detection challenges. A key novelty of this work lies in the detailed examination of computational complexities in IDS deployment, including sensor fusion methods, noise reduction techniques, and false alarm mitigation strategies, which are often overlooked in previous surveys. We also explore deep learning-based IDS, providing a comparative evaluation of simulated versus real-world performance. Additionally, we present an in-depth discussion on post-quantum cryptographic techniques and blockchain integration for enhancing security in Federated Learning-based IDS. This survey bridges the gap between theoretical IDS models and real-world V2X deployment, addressing key constraints such as energy efficiency, communication overhead, and scalability in resource-constrained vehicular networks. By studying the state-of-the-art methodologies, identifying critical research gaps, and proposing practical advancements, this paper serves as a definitive resource for researchers,and industry professionals, guiding the development of robust, adaptive, and privacy-preserving IDS solutions for next-generation autonomous and connected vehicles (CAVs).

Overview

Integrity signals

Registry

Crossref · 10.1109/tits.2025.3558849

Cites

235 of 235 references verified0 citation errors · 0 not checkable

Statistics

Recomputing p-values needs the paper’s full text.

Verification

Claims the paper makes

This paper’s full text isn’t openly available, so its claims and self-check weren’t run. The registry and citation checks still apply.

Citations

Cites

Show all 238 references

Research works printed but not linked: 20

  1. Naserian, 2018, Detecting misbehavior in vehicle-to-vehicle communications
  2. 2025, IDS Intrusion CSV
  3. 2025, Veremi Dataset
  4. 2028, Intrusion Detection Evaluation Dataset (CSE-CIC-IDS2018)
  5. 2024, The UNSW-NB15 Dataset
  6. 2024, CAN Dataset for intrusion detection (OTIDS)
  7. 2024, Car-Hacking Dataset
  8. Korba, 2024, Federated learning-based intrusion detection in vehicular networks, IEEE Trans. Veh. Technol., 73, 2456
  9. Zhou, 2024, Privacy-preserving federated learning for autonomous vehicles, IEEE Internet Things J., 11, 6783
  10. Li, 2024, Federated intrusion detection for V2X networks: Challenges and solutions, Comput. Netw., 225
  11. Huang, 2024, An execution & evaluation dual-network FL framework for edge security in IoT, IEEE Trans. Dependable Secure Comput., 21, 89
  12. Raza, 2024, SDN-enabled federated learning for secure V2X communication, IEEE Trans. Mobile Comput., 23, 1347
  13. Samy, 2024, Edge AI-based real-time intrusion detection for smart vehicles, IEEE Trans. Intell. Transp. Syst., 25, 3401
  14. Alladi, 2024, MEC-enabled intrusion detection systems for secure V2X networks, IEEE Trans. Netw. Service Manage., 21, 211
  15. Hasan, 2024, Lightweight federated learning for energy-efficient IoT security, IEEE Access, 12, 7456
  16. Bangui, 2024, Hybrid AI-driven security mechanism for V2X networks, ACM Trans. Cyber-Phys. Syst., 8, 56
  17. Taslimasa, 2024, ImageFed: Federated learning for cyberattack detection in autonomous vehicles, IEEE Trans. Artif. Intell., 5, 312
  18. Bhavsar, 2024, Blockchain-enhanced federated learning for secure vehicular networks, IEEE Trans. Inf. Forensics Security, 19, 1458
  19. Rajak, An attack detection model for enhancing the security of 5G-enabled vehicle-to-everything (V2X) communication for smart vehicles, 229
  20. Jiménez, 2022, Deep learning-based cyber attack detection in autonomous vehicle networks, J. AI-Assist. Sci. Discovery, 2, 1

Cited by

See all 90

Metadata

Authors
Abdel Hakeem, S. A., & Kim, H.
Affiliations
  • Department of Electronics Engineering, College of Electrical and Computer Engineering, Chungbuk National University, Cheongju, South Korea
  • Chungbuk National University (KR)
Venue
IEEE Transactions on Intelligent Transportation Systems
Published
2025-08
Volume
26
Issue
8
Pages
11137-11205
ISSN
  • 1524-9050 (ISSN-L)
  • 1558-0016
OpenAlex
W4410638774
Cited by
90
References
238
Citations by year
2026: 69 · 2025: 21
FWCI
37.33
Type
journal article
Language
en
Open access
closed
Locations
IEEE Transactions on Intelligent Transportation Systems (publishedVersion)
Topics
  • Physical Sciences › Computer Science › Computer Networks and Communications › Network Security and Intrusion Detection
  • Physical Sciences › Engineering › Electrical and Electronic Engineering › Vehicular Ad Hoc Networks (VANETs)
  • Physical Sciences › Computer Science › Artificial Intelligence › Adversarial Robustness in Machine Learning
Keywords
V2X networks, intrusion detection systems, VANET security, federated learning, edge AI, adversarial robustness, data poisoning, evasion attacks, false alarm reduction, sensor fusion, intrusion detection datasets, zero-day attacks, post-quantum cryptography, blockchain, connected and autonomous vehicles, computational complexity

About these checks

Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.

Statistics and arithmetic are recomputed, not judged.

Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.

What counts as a claim ›How we measure confidence ›How we check this ›

Are you an author, or do you see a problem with this page? Request a review

How to cite

Cite CoChat for the checks on this page, and the paper for its own findings.

This page
CoChat. (2026). Citation check: Advancing Intrusion Detection in V2X Networks: A Comprehensive Survey on Machine Learning, Federated Learning, and Edge AI for V2X Security. https://app.cochat.ai/papers/10.1109/tits.2025.3558849
The paper
Abdel Hakeem, S. A., & Kim, H. (2025). Advancing Intrusion Detection in V2X Networks: A Comprehensive Survey on Machine Learning, Federated Learning, and Edge AI for V2X Security. IEEE Transactions on Intelligent Transportation Systems. https://doi.org/10.1109/tits.2025.3558849

Data sources

Bibliographic data: Semantic Scholar, OpenAlex, Crossref.

Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).

Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.