SENTAUR: Security EnhaNced Trojan Assessment Using LLMs Against Undesirable Revisions

TL;DR

SENTAUR leverages large language models to rapidly generate and assess hardware Trojan scenarios in RTL designs, improving detection and understanding of stealthy malicious modifications in integrated circuits.

Contribution

The paper introduces SENTAUR, a novel LLM-based framework that generates legitimate hardware Trojan instances without prior training, enhancing the speed and reproducibility of security assessments.

Findings

SENTAUR can generate effective, synthesizable HTs from TrustHub and other sources.

It facilitates rapid assessment of HT payloads and triggers at the RTL level.

SENTAUR can also transform RTL code to include specific functional modifications.

Abstract

A globally distributed IC supply chain brings risks due to untrusted third parties. The risks span inadvertent use of hardware Trojan (HT), inserted Intellectual Property (3P-IP) or Electronic Design Automation (EDA) flows. HT can introduce stealthy HT behavior, prevent an IC work as intended, or leak sensitive data via side channels. To counter HTs, rapidly examining HT scenarios is a key requirement. While Trust-Hub benchmarks are a good starting point to assess defenses, they encompass a small subset of manually created HTs within the expanse of HT designs. Further, the HTs may disappear during synthesis. We propose a large language model (LLM) framework SENTAUR to generate a suite of legitimate HTs for a Register Transfer Level (RTL) design by learning its specifications, descriptions, and natural language descriptions of HT effects. Existing tools and benchmarks are limited; they need a learning period to construct an ML model to mimic the threat model and are difficult to reproduce. SENTAUR can swiftly produce HT instances by leveraging LLMs without any learning period and sanitizing the HTs facilitating their rapid assessment. Evaluation of SENTAUR involved generating effective, synthesizable, and practical HTs from TrustHub and elsewhere, investigating impacts of payloads/triggers at the RTL. While our evaluation focused on HT insertion, SENTAUR can generalize to automatically transform an RTL code to have defined functional modifications.