The Controller Area Network (CAN) is the most widely used in-vehicle communication protocol, which still lacks the implementation of suitable security mechanisms such as message authentication and encryption. This makes the CAN bus vulnerable to numerous cyber attacks. Various Intrusion Detection Systems (IDSs) have been developed to detect these attacks. However, the high generalization capabilities of Artificial Intelligence (AI) make AI-based IDS an excellent countermeasure against automotive cyber attacks. This article surveys AI-based in-vehicle IDS from 2016 to 2022 (August) with a novel taxonomy. It reviews the detection techniques, attack types, features, and benchmark datasets. Furthermore, the article discusses the security of AI models, necessary steps to develop AI-based IDSs in the CAN bus, identifies the limitations of existing proposals, and gives recommendations for future research directions.

控制器局域网（CAN）是应用最广泛的车载通信协议，但仍缺乏适当的安全机制（例如消息认证和加密）的实现。这使得 CAN 总线容易受到大量网络攻击。已经开发了各种入侵检测系统 (IDS) 来检测这些攻击。然而，人工智能 (AI) 的高度泛化能力使基于 AI 的 IDS 成为应对汽车网络攻击的绝佳对策。本文使用一种新颖的分类法调查了 2016 年至 2022 年（8 月）期间基于 AI 的车载 IDS。它回顾了检测技术、攻击类型、特征和基准数据集。此外，本文还讨论了 AI 模型的安全性、在 CAN 总线中开发基于 AI 的 IDS 的必要步骤，