This research introduces a novel LLM-powered approach to Information Flow Tracking (IFT) that significantly improves hardware security verification and vulnerability detection.

• Combines Large Language Models with IFT to automatically trace sensitive data flow across complex hardware designs
• Achieves 92.8% accuracy in identifying security vulnerabilities while reducing manual effort
• Demonstrates superior adaptability to diverse hardware architectures compared to traditional methods
• Provides scalable solutions for increasingly complex modern hardware designs

This advancement matters because it helps address critical security challenges in hardware design where traditional methods struggle with complexity and adaptability, potentially preventing major security breaches in critical systems.

LLM-IFT: LLM-Powered Information Flow Tracking for Secure Hardware