SecureRAG-RTL: A Retrieval-Augmented, Multi-Agent, Zero-Shot LLM-Driven Framework for Hardware Vulnerability Detection
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2026
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866915838461739008 |
|---|---|
| author | Hasan, Touseef Airehenbuwa, Blessing Pundir, Nitin Sarkar, Souvika Guin, Ujjwal |
| author_facet | Hasan, Touseef Airehenbuwa, Blessing Pundir, Nitin Sarkar, Souvika Guin, Ujjwal |
| contents | Large language models (LLMs) have shown remarkable capabilities in natural language processing tasks, yet their application in hardware security verification remains limited due to scarcity of publicly available hardware description language (HDL) datasets. This knowledge gap constrains LLM performance in detecting vulnerabilities within HDL designs. To address this challenge, we propose SecureRAG-RTL, a novel Retrieval-Augmented Generation (RAG)-based approach that significantly enhances LLM-based security verification of hardware designs. Our approach integrates domain-specific retrieval with generative reasoning, enabling models to overcome inherent limitations in hardware security expertise. We establish baseline vulnerability detection rates using prompt-only methods and then demonstrate that SecureRAG-RTL achieves substantial improvements across diverse LLM architectures, regardless of size. On average, our method increases detection accuracy by about 30%, highlighting its effectiveness in bridging domain knowledge gaps. For evaluation, we curated and annotated a benchmark dataset of 14 HDL designs containing real-world security vulnerabilities, which we will release publicly to support future research. These findings underscore the potential of RAG-driven augmentation to enable scalable, efficient, and accurate hardware security verification workflows. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2603_05689 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | SecureRAG-RTL: A Retrieval-Augmented, Multi-Agent, Zero-Shot LLM-Driven Framework for Hardware Vulnerability Detection Hasan, Touseef Airehenbuwa, Blessing Pundir, Nitin Sarkar, Souvika Guin, Ujjwal Cryptography and Security Artificial Intelligence Large language models (LLMs) have shown remarkable capabilities in natural language processing tasks, yet their application in hardware security verification remains limited due to scarcity of publicly available hardware description language (HDL) datasets. This knowledge gap constrains LLM performance in detecting vulnerabilities within HDL designs. To address this challenge, we propose SecureRAG-RTL, a novel Retrieval-Augmented Generation (RAG)-based approach that significantly enhances LLM-based security verification of hardware designs. Our approach integrates domain-specific retrieval with generative reasoning, enabling models to overcome inherent limitations in hardware security expertise. We establish baseline vulnerability detection rates using prompt-only methods and then demonstrate that SecureRAG-RTL achieves substantial improvements across diverse LLM architectures, regardless of size. On average, our method increases detection accuracy by about 30%, highlighting its effectiveness in bridging domain knowledge gaps. For evaluation, we curated and annotated a benchmark dataset of 14 HDL designs containing real-world security vulnerabilities, which we will release publicly to support future research. These findings underscore the potential of RAG-driven augmentation to enable scalable, efficient, and accurate hardware security verification workflows. |
| title | SecureRAG-RTL: A Retrieval-Augmented, Multi-Agent, Zero-Shot LLM-Driven Framework for Hardware Vulnerability Detection |
| topic | Cryptography and Security Artificial Intelligence |
| url | https://arxiv.org/abs/2603.05689 |