SVAgent: AI Agent for Hardware Security Verification Assertion

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Guo, Rui, Ayalasomayajula, Avinash, Li, Henian, Zhou, Jingbo, Saha, Sujan Kumar, Farahmandi, Farimah
Formato: Preprint
Publicado: 2025
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866912496459186176
author Guo, Rui
Ayalasomayajula, Avinash
Li, Henian
Zhou, Jingbo
Saha, Sujan Kumar
Farahmandi, Farimah
author_facet Guo, Rui
Ayalasomayajula, Avinash
Li, Henian
Zhou, Jingbo
Saha, Sujan Kumar
Farahmandi, Farimah
contents Verification using SystemVerilog assertions (SVA) is one of the most popular methods for detecting circuit design vulnerabilities. However, with the globalization of integrated circuit design and the continuous upgrading of security requirements, the SVA development model has exposed major limitations. It is not only inefficient in development, but also unable to effectively deal with the increasing number of security vulnerabilities in modern complex integrated circuits. In response to these challenges, this paper proposes an innovative SVA automatic generation framework SVAgent. SVAgent introduces a requirement decomposition mechanism to transform the original complex requirements into a structured, gradually solvable fine-grained problem-solving chain. Experiments have shown that SVAgent can effectively suppress the influence of hallucinations and random answers, and the key evaluation indicators such as the accuracy and consistency of the SVA are significantly better than existing frameworks. More importantly, we successfully integrated SVAgent into the most mainstream integrated circuit vulnerability assessment framework and verified its practicality and reliability in a real engineering design environment.
format Preprint
id arxiv_https___arxiv_org_abs_2507_16203
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle SVAgent: AI Agent for Hardware Security Verification Assertion
Guo, Rui
Ayalasomayajula, Avinash
Li, Henian
Zhou, Jingbo
Saha, Sujan Kumar
Farahmandi, Farimah
Cryptography and Security
Artificial Intelligence
Hardware Architecture
Machine Learning
Verification using SystemVerilog assertions (SVA) is one of the most popular methods for detecting circuit design vulnerabilities. However, with the globalization of integrated circuit design and the continuous upgrading of security requirements, the SVA development model has exposed major limitations. It is not only inefficient in development, but also unable to effectively deal with the increasing number of security vulnerabilities in modern complex integrated circuits. In response to these challenges, this paper proposes an innovative SVA automatic generation framework SVAgent. SVAgent introduces a requirement decomposition mechanism to transform the original complex requirements into a structured, gradually solvable fine-grained problem-solving chain. Experiments have shown that SVAgent can effectively suppress the influence of hallucinations and random answers, and the key evaluation indicators such as the accuracy and consistency of the SVA are significantly better than existing frameworks. More importantly, we successfully integrated SVAgent into the most mainstream integrated circuit vulnerability assessment framework and verified its practicality and reliability in a real engineering design environment.
title SVAgent: AI Agent for Hardware Security Verification Assertion
topic Cryptography and Security
Artificial Intelligence
Hardware Architecture
Machine Learning
url https://arxiv.org/abs/2507.16203