arXiv：cs.LG· Konstantinos Gyftodimos, Kyriakos Chiotis, Elena Politi, George Dimitrakopoulos, Eirini Liotou·· 3 小时前
基于时间 Transformer CAN 编码器与联邦轻量头的车载网络异常检测框架
Temporal transformer CAN encoder with federated lightweight heads for anomaly detection
AI 导读
研究者提出一种隐私保护的车载网络异常检测框架，由时间 Transformer CAN 编码器和联邦轻量头组成，用轻量 Transformer 编码器学习 CAN 信号随时间的演化，捕捉细微的时序与上下文异常，联邦学习机制让多辆车辆或 ECU 在不交换原始 CAN 数据的前提下协同改进共享模型。在开源数据集上的实验显示，该方案在保持效率与隐私的同时实现了稳健的异常检测性能。
正文
Abstract:Modern vehicles rely on large numbers of Electronic Control Units (ECUs) that constantly exchange information over the Controller Area Network (CAN) bus. Due to the rapidity, structure, and repetition of this communication, even slight variations in timing, payload values, or message patterns can point to unusual activity. Whether due to errors, malfunctions, or deliberate interference, these anomalies are frequently subtle and challenging to identify with conventional methods that handle messages separately or rely on manually created rules. Motivated by this gap, we present a privacy-preserving framework for anomaly detection in in-vehicle networks, based on a Temporal Transformer CAN Encoder with Federated Lightweight Heads, to better capture these irregularities. The detection of subtle temporal and contextual anomalies is made possible by a lightweight Transformer encoder that learns how these signals evolve over time, while a federated learning mechanism enables several vehicles or ECUs to work together to improve a shared model without exchanging raw CAN data. This combination of federated learning and temporal sequence modeling provides robust anomaly detection performance while maintaining efficiency and privacy, according to experiments conducted on open-source datasets.
| Subjects: | Machine Learning (cs.LG); Cryptography and Security (cs.CR) |
| Cite as: | arXiv:2610.10613 [cs.LG] |
| (or arXiv:2610.10613v1 [cs.LG] for this version) | |
| https://doi.org/10.48550/arXiv.2610.10613 arXiv-issued DOI via DataCite |
|
| Journal reference: | Presented at ITS European Congress 2025 |
Submission history
From: Eirini Liotou Dr. [view email]
[v1]
Wed, 7 Oct 2026 07:13:20 UTC (474 KB)
来源：arXiv：cs.LG · arxiv.org