基于关联规则与离群点的新能源汽车动力域入侵检测

为提高新能源汽车动力域中针对篡改攻击的入侵检测系统效果，建立包括关联规则检测和离群点检测的动力域防护模型，通过实车采集固定工况下的动力域报文数据，基于关联规则算法建立规则库检测篡改攻击；在关联规则检测的基础上通过离群点检测，检测复杂类型的篡改攻击。仿真结果表明，该方法相比于传统的关联规则方法检测准确率提高5.83%，能有效检测针对新能源汽车动力域的篡改攻击。

Intrusion Detection in New Energy Vehicle Power Domains Based on Association Rules and Outlier Detection

To improve the effectiveness of intrusion detection systems against tampering attacks in the power domain of new energy vehicles, a power domain protection model is established, including both association rule detection and outlier detection. By collecting the power domain messages from the actual vehicles and establishing a rule base using the association rule algorithm, this model aims to detect tampering attacks. On the basis of association rule detection, complex types of tampering attacks are identified through outlier detection. The simulation results show that this method improves the detection accuracy by 5.83% compared to traditional association rule methods, effectively detecting tampering attacks in the power domain of new energy vehicles.