Cross-Domain Adversarial Attacks: Translating Network Intrusion to CAN Bus Evasion in V2X Environments

This research paper presents an attack framework between NIDS and CAN-based intrusion detection that secures vehicle-to-everything (V2X) environments. The connection of vehicles to external networks exposes critical security concerns because public network attacks can penetrate into vehicle systems. Our methodology performs three steps to enable crossdomain attacks through network security domain and automotive security domain integration: (1) ensemble feature selection discovering common vulnerabilities, (2) V2X-Aware calibrated gradient descent that follows protocol constraints, and (3) CAN-Deep PackGen produces valid network-based CAN frames. Our attacks achieve evasion rates of up to 87.9% during experiments on KDDCup99 and UNSW-NB15 for NIDS and CICIoV2024 for CAN IDS. The transfer success rate for timing-related features surpasses 85% due to their vulnerability. The attack success rate receives 24.7% improvement from ensemble feature selection which exhibits strong correlation with feature importance in predicting attack transferability. The diagnostic CAN messages demonstrate the maximum vulnerability to attacks by achieving a <tex xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">$\text{9 2. 3 \%}$</tex> evasion rate. These findings highlight critical security implications for connected vehicles and demonstrate the need for cross-domain defensive strategies in automotive cybersecurity, providing a foundation for understanding and mitigating adversarial threats in interconnected transportation.