LLMs used to identify IoT devices at scale with high accuracy

Researchers have developed a novel method for identifying Internet of Things (IoT) devices at scale by treating network traffic metadata as a language modeling task. They constructed a high-fidelity dataset of vendor labels using large language models and then instruction-tuned a LLaMA 3.1 8B model on this data. This approach achieved high accuracy in device identification, demonstrating robustness against missing data, protocol drift, and adversarial manipulation, positioning LLMs as a scalable foundation for trustworthy IoT device identification. AI

IMPACT This research offers a scalable and interpretable method for identifying IoT devices, potentially improving network security and privacy.

RANK_REASON Academic paper detailing a new methodology for device identification using LLMs. [lever_c_demoted from research: ic=1 ai=1.0]

Read on arXiv cs.LG →

• IoT devices
• IoT Inspector dataset
• Large Language Models
• LLaMA 3.1 8B
• Rameen Mahmood

• paper
• product
• infra

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