Unleashing GHOST: An LLM-Powered Framework for Automated Hardware Trojan Design

TL;DR

GHOST leverages Large Language Models to automate hardware Trojan design, significantly reducing manual effort and enabling rapid, stealthy insertion of functional HTs that evade existing detection tools, raising new security concerns.

Contribution

This paper introduces GHOST, a novel LLM-powered framework for automated hardware Trojan generation, demonstrating its effectiveness across multiple hardware designs and LLMs.

Findings

GPT-4 achieves 88.88% success in HT insertion

100% of GHOST-generated HTs evade detection

LLMs can rapidly generate functional, stealthy HTs

Abstract

Traditionally, inserting realistic Hardware Trojans (HTs) into complex hardware systems has been a time-consuming and manual process, requiring comprehensive knowledge of the design and navigating intricate Hardware Description Language (HDL) codebases. Machine Learning (ML)-based approaches have attempted to automate this process but often face challenges such as the need for extensive training data, long learning times, and limited generalizability across diverse hardware design landscapes. This paper addresses these challenges by proposing GHOST (Generator for Hardware-Oriented Stealthy Trojans), an automated attack framework that leverages Large Language Models (LLMs) for rapid HT generation and insertion. Our study evaluates three state-of-the-art LLMs - GPT-4, Gemini-1.5-pro, and Llama-3-70B - across three hardware designs: SRAM, AES, and UART. According to our evaluations, GPT-4 demonstrates superior performance, with 88.88% of HT insertion attempts successfully generating functional and synthesizable HTs. This study also highlights the security risks posed by LLM-generated HTs, showing that 100% of GHOST-generated synthesizable HTs evaded detection by an ML-based HT detection tool. These results underscore the urgent need for advanced detection and prevention mechanisms in hardware security to address the emerging threat of LLM-generated HTs. The GHOST HT benchmarks are available at: https://github.com/HSTRG1/GHOSTbenchmarks.git