SVAgent: AI Agent for Hardware Security Verification Assertion

2025/07/22 by Rui Guo, Guo, Rui, Avinash Ayalasomayajula +9 · 1 citation
Computer Science · #Advanced Malware Detection Techniques #Adversarial Robustness in Machine Learning #Artificial Intelligence (cs.AI) #Cryptography and Security (cs.CR) #FOS: Computer and information sciences #Hardware Architecture (cs.AR) #Machine Learning (cs.LG)

paper · pdf · doi:10.48550/arxiv.2507.16203

openalex publication_date 2025/07/22 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

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.

Citations

• Attend First, Consolidate Later: On the Importance of Attention in Different LLM Layers
• Understanding the Performance and Estimating the Cost of LLM Fine-Tuning
• Bugs in Large Language Models Generated Code: An Empirical Study
• Executable Code Actions Elicit Better LLM Agents
• ChIRAAG: ChatGPT Informed Rapid and Automated Assertion Generation
• Data-efficient Fine-tuning for LLM-based Recommendation
• DIVAS: An LLM-based End-to-End Framework for SoC Security Analysis and Policy-based Protection
• VeriGen: A Large Language Model for Verilog Code Generation
• GPT-4 Can't Reason
• Full Parameter Fine-tuning for Large Language Models with Limited Resources
• A Mathematical Investigation of Hallucination and Creativity in GPT Models
• PaLM-E: An Embodied Multimodal Language Model
• MathPrompter: Mathematical Reasoning using Large Language Models
• A Prompt Pattern Catalog to Enhance Prompt Engineering with ChatGPT
• Is ChatGPT a General-Purpose Natural Language Processing Task Solver?
• Emergent Analogical Reasoning in Large Language Models
• Asleep at the Keyboard? Assessing the Security of GitHub Copilot's Code Contributions
• A Survey of Microarchitectural Side-channel Vulnerabilities, Attacks and Defenses in Cryptography
• In-IDE Code Generation from Natural Language: Promise and Challenges
• A Dynamic LLM-Powered Agent Network for Task-Oriented Agent Collaboration

Cited by

• CHARGE: Leveraging CWE Hierarchies for Hardware Security SystemVerilog Assertion Generation

Related

• SV-LLM: An Agentic Approach for SoC Security Verification using Large Language Models
• The Emergence of Hardware Fuzzing: A Critical Review of its Significance
• All Artificial, Less Intelligence: GenAI through the Lens of Formal Verification
• BugWhisperer: Fine-Tuning LLMs for SoC Hardware Vulnerability Detection
• LASA: Enhancing SoC Security Verification with LLM-Aided Property Generation