New SPADE dataset targets deep learning for connected vehicle SPaT message security

Researchers have introduced SPADE, a new dataset designed for deep learning-based intrusion detection systems focused on connected vehicle safety. SPADE addresses the vulnerability of Signal Phase and Timing (SPaT) messages, which are crucial for vehicles to understand intersection states but can be compromised by application-layer attacks. The dataset, generated using Eclipse MOSAIC, includes approximately 1.89 million labeled timestep records across six attack classes and one benign class, fusing SPaT message fields, camera confidence scores, and V2V peer data. This resource aims to support reproducible research in C-V2X security by providing a publicly available dataset, generation code, and scenario configurations. AI

IMPACT This dataset could accelerate the development of more robust AI-powered security systems for connected vehicles, enhancing safety and trust in V2X communications.

RANK_REASON The cluster describes a new dataset and associated code for deep learning-based intrusion detection research in a specific domain (connected vehicles).

Read on arXiv cs.LG →

• connected vehicle
• C-V2X security
• deep learning
• Eclipse MOSAIC
• GitHub
• intrusion detection systems
• SAE J2735
• Signal Phase and Timing (SPaT) messages
• Spade
• Vehicle-to-Infrastructure (V2I)
• Signal Phase and Timing
• SPaT Attack Detection and Evaluation dataset
• Vehicle-to-Infrastructure communication

• paper
• product
• safety

AI-generated summary · Google Gemini · from 2 sources. How we write summaries →