核心概念
Proposing MKF-ADS for efficient anomaly detection in automotive systems.
要約
The paper introduces MKF-ADS, a novel anomaly detection system for automotive security. It addresses the vulnerabilities in Controller Area Network (CAN) bus communication and proposes a multi-knowledge fused model for anomaly detection. The system combines spatial-temporal correlation and patch sparse-transformer modules to enhance detection efficiency and reduce false alarms. Extensive experiments show competitive performance in detecting various attack scenarios.
統計
"Compared with the baseline in the same paradigm, the error rate and FAR are 2.62% and 2.41% and achieve a promising F1-score of 97.3%."
"The dataset was collected via the OBD-II port connected by real-world vehicles."
"The model was carried out on Intel(R) Core (TM) i7-9500U CPU@3.6GHZ, 64 GB of RAM, and GPU RTX 3090."
引用
"In this paper, we propose a novel multi-knowledge fused anomaly detection model, called MKF-IDS."
"The proposed method is based on knowledge distillation to STcAM as a student model for learning intrinsic knowledge and cross the ability to mimic PatchST."