Small Language Models Detect GNSS Spoofing Attacks in Autonomous Vehicles

Researchers have developed a framework using small language models (SLMs) to detect and classify Global Navigation Satellite System (GNSS) spoofing attacks in autonomous vehicles. This method converts driving state data from GNSS and other sensors into semantic narratives for SLMs, achieving high accuracy (96.99%) in identifying various attack types. The SLM-based approach offers significant advantages in computational efficiency and resource utilization compared to larger language models, making it suitable for deployment on resource-constrained vehicular platforms. AI

IMPACT This research could enhance the security and reliability of autonomous vehicle navigation systems by providing efficient spoofing detection capabilities.

RANK_REASON The cluster contains an academic paper detailing a new method for GNSS spoofing detection using SLMs. [lever_c_demoted from research: ic=1 ai=1.0]

Read on arXiv cs.AI →

• arXiv
• Clemson
• global navigation satellite system
• large language model
• small language model
• South Carolina
• United States

• paper
• safety
• product

AI-generated summary · Google Gemini · from 1 sources. How we write summaries →