A Dynamic Traffic Camouflage Method Based on Adversarial Machine Learning for Connected Vehicles
Open Access
- 23 February 2026
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Open Journal of Vehicular Technology
- Vol. 7, 887-900
Abstract
While improving the convenience of Internet of Vehicles applications, its communication process faces serious privacy and security threats. Especially in the process of network layer transmission, the analysis of side-channel characteristics (such as packet size and traffic transmission mode) may lead to user privacy leakage. Most of the existing research focuses on website fingerprint camouflage or overall traffic statistical feature camouflage, and usually only designs a camouflage mechanism for a single application layer protocol, which is challenging to achieve unified protection in the multi-protocol scenario of the Internet of Vehicles. In this paper, we propose a method called LeakGAN Packets Traffic Camouflage (LPTC), which can provide traffic camouflage for multiple application-layer protocols simultaneously. The LPTC learns the sending pattern of target traffic packets and generates camouflaged traffic through an adversarial game between a generator and a discriminator, to effectively resist side-channel attacks without affecting communication performance. Experimental results indicate that the proposed LPTC scheme significantly degrades the classification performance of traffic transmission models based on K-Nearest Neighbors, Support Vector Machine, Bagged Trees, and Random Forest algorithms, reducing classification accuracy by 41.23%. In addition, the precision, recall, F1 score, and AUC value decreased by 41.82%, 61.85%, 49.57%, and 42.00%, respectively. Moreover, the LPTC can effectively withstand adaptive attackers who retrain deep learning classifiers on camouflaged traffic. The LPTC substantially enhances the indistinguishability between target and camouflaged traffic, thereby effectively mitigating user privacy leakage caused by side-channel analysis. Meanwhile, the system's bandwidth and delay performance is sufficient to support the transmission requirements of real-time vehicular networks.Keywords
Funding Information
- National Natural Science Foundation of China (62394321)
- Fundamental Research Funds for the Central Universities (I24JBGP00020)
- National Key R&D Program of China (2022ZD0115301)
This publication has 24 references indexed in Scilit:
- Internet of Vehicles Security Threats, Countermeasures, Open Challenges With Future Research DirectionsIEEE Internet of Things Journal, 2025
- Unmasking the Internet: A Survey of Fine-Grained Network Traffic AnalysisIEEE Communications Surveys & Tutorials, 2025
- A Review on Security Challenges in V2X Communications Technology for VANETsIEEE Access, 2025
- Vehicle-to-Everything Communication in Intelligent Connected Vehicles: A Survey and TaxonomyAutomotive Innovation, 2025
- Practical and lightweight defense against website fingerprintingComputer Communications, 2024
- A Comprehensive Survey of V2X Cybersecurity Mechanisms and Future Research PathsIEEE Open Journal of the Communications Society, 2023
- Adversarial Machine Learning for Network Intrusion Detection Systems: A Comprehensive SurveyIEEE Communications Surveys & Tutorials, 2023
- Machine Learning-Powered Encrypted Network Traffic Analysis: A Comprehensive SurveyIEEE Communications Surveys & Tutorials, 2022
- VPN Traffic Identification Based on Tunneling Protocol Characteristics2022
- Long Short-Term Memory2012