The Internet of Vehicles' reliance on Controller Area Network (CAN) communication introduces significant security risks due to its vulnerability to cyberattacks. To address this, researchers have developed DAIRE, a lightweight machine learning framework for real-time detection of CAN-based attacks. DAIRE is designed to identify potential threats in the IoV ecosystem, leveraging its machine learning capabilities to flag suspicious activity. The model's lightweight architecture enables efficient deployment in resource-constrained IoV environments, making it an attractive solution for real-time threat detection. By detecting attacks in real-time, DAIRE can help prevent potential disruptions to vehicle safety and efficiency1. This matters to cybersecurity practitioners because the ability to detect and respond to CAN-based attacks in real-time is critical to ensuring the security and reliability of the Internet of Vehicles.