LLM-Assisted Detection and Repair of Hardware Security Vulnerabilities in Verilog Designs

• URL: http://arxiv.org/abs/2608.04907v1
• Date: Wed, 05 Aug 2026 14:35:41 GMT
• Title: LLM-Assisted Detection and Repair of Hardware Security Vulnerabilities in Verilog Designs
• Abstract summary: We propose a methodology that leverages a Large Language Model (LLM) to identify potential hardware CWEs directly from hardware designs in Verilog.<n>Our results demonstrate the potential of LLMs to augment traditional hardware security analysis by providing automated, scalable assistance for identifying security vulnerabilities during the hardware design process.
• Score: 5.354071922171165
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Hardware designs, like software, are susceptible to bugs that can introduce security vulnerabilities and create opportunities for malicious exploitation. Unlike software vulnerabilities, however, hardware flaws become permanently embedded in silicon after fabrication, making them difficult or impossible to patch. Many of these weaknesses are categorized under the Common Weakness Enumeration (CWE) framework and include improper access control, exposure of sensitive information, and unintended privilege escalation. To improve the detection of such vulnerabilities, we propose a methodology that leverages a Large Language Model (LLM) to identify potential hardware CWEs directly from hardware designs in Verilog. The proposed approach is evaluated iteratively on a dataset of single-module Verilog designs to assess its effectiveness in detecting hardware security weaknesses. Our results demonstrate the potential of LLMs to augment traditional hardware security analysis by providing automated, scalable assistance for identifying security vulnerabilities during the hardware design process.

Related papers

• SecureRAG-RTL: A Retrieval-Augmented, Multi-Agent, Zero-Shot LLM-Driven Framework for Hardware Vulnerability Detection [1.4675092799855405]
  Large language models (LLMs) have shown remarkable capabilities in natural language processing tasks.<n>We propose SecureRAG-RTL, a novel Retrieval-Augmented Generation (RAG)-based approach.<n>Our approach integrates domain-specific retrieval with generative reasoning, enabling models to overcome inherent limitations in hardware security expertise.
  arXiv  Detail & Related papers  (2026-03-05T21:25:49Z)
• An Empirical Study on the Security Vulnerabilities of GPTs [48.12756684275687]
  GPTs are one kind of customized AI agents based on OpenAI's large language models.<n>We present an empirical study on the security vulnerabilities of GPTs.
  arXiv  Detail & Related papers  (2025-11-28T13:30:25Z)
• Certifiably robust malware detectors by design [48.367676529300276]
  We propose a new model architecture for robust malware detection by design.<n>We show that every robust detector can be decomposed into a specific structure, which can be applied to learn empirically robust malware detectors.<n>Our framework ERDALT is based on this structure.
  arXiv  Detail & Related papers  (2025-08-10T09:19:29Z)
• CANDoSA: A Hardware Performance Counter-Based Intrusion Detection System for DoS Attacks on Automotive CAN bus [45.24207460381396]
  This paper presents a novel Intrusion Detection System (IDS) designed for the Controller Area Network (CAN) environment.<n>A RISC-V-based CAN receiver is simulated using the gem5 simulator, processing CAN frame payloads with AES-128 encryption as FreeRTOS tasks.<n>Results indicate that this approach could significantly improve CAN security and address emerging challenges in automotive cybersecurity.
  arXiv  Detail & Related papers  (2025-07-19T20:09:52Z)
• BugWhisperer: Fine-Tuning LLMs for SoC Hardware Vulnerability Detection [1.0816123715383426]
  This paper proposes a new framework named BugWhisperer to address the challenges of system-on-chips (SoCs) security verification.<n>We introduce an open-source, fine-tuned Large Language Model (LLM) specifically designed for detecting security vulnerabilities in SoCs.
  arXiv  Detail & Related papers  (2025-05-28T21:25:06Z)
• Transformers for Secure Hardware Systems: Applications, Challenges, and Outlook [2.9625426098772425]
  Transformer models have gained traction in the security domain due to their ability to model complex dependencies.<n>This survey provides a review of recent advancements on the use of Transformers in hardware security.<n>It examines their application across key areas such as side-channel analysis, hardware Trojan detection, vulnerability classification, device fingerprinting, and firmware security.
  arXiv  Detail & Related papers  (2025-05-28T17:22:14Z)
• The Impact of SBOM Generators on Vulnerability Assessment in Python: A Comparison and a Novel Approach [56.4040698609393]
  Software Bill of Materials (SBOM) has been promoted as a tool to increase transparency and verifiability in software composition. Current SBOM generation tools often suffer from inaccuracies in identifying components and dependencies. We propose PIP-sbom, a novel pip-inspired solution that addresses their shortcomings.
  arXiv  Detail & Related papers  (2024-09-10T10:12:37Z)
• The Emergence of Hardware Fuzzing: A Critical Review of its Significance [0.4943822978887544]
  Hardware fuzzing, inspired by software testing methodologies, has gained prominence for its efficacy in identifying bugs within complex hardware designs. Despite the introduction of various hardware fuzzing techniques, obstacles such as inefficient conversion of hardware modules into software models impede their effectiveness. This work examines the reliability of existing hardware fuzzing techniques in identifying vulnerabilities and identifies research gaps for future advancements in design verification techniques.
  arXiv  Detail & Related papers  (2024-03-19T15:12:11Z)
• HW-V2W-Map: Hardware Vulnerability to Weakness Mapping Framework for Root Cause Analysis with GPT-assisted Mitigation Suggestion [3.847218857469107]
  We presentHW-V2W-Map Framework, which is a Machine Learning (ML) framework focusing on hardware vulnerabilities and Internet of Things (IoT) security. The architecture that we have proposed incorporates an Ontology-driven Storytelling framework, which automates the process of updating the Ontology. Our proposed framework utilized Generative Pre-trained Transformer (GPT) Large Language Models (LLMs) to provide mitigation suggestions.
  arXiv  Detail & Related papers  (2023-12-21T02:14:41Z)
• A survey on hardware-based malware detection approaches [45.24207460381396]
  Hardware-based malware detection approaches leverage hardware performance counters and machine learning prowess. We meticulously analyze the approach, unraveling the most common methods, algorithms, tools, and datasets that shape its contours. The discussion extends to crafting mixed hardware and software approaches for collaborative efficacy, essential enhancements in hardware monitoring units, and a better understanding of the correlation between hardware events and malware applications.
  arXiv  Detail & Related papers  (2023-03-22T13:00:41Z)
• Dos and Don'ts of Machine Learning in Computer Security [74.1816306998445]
  Despite great potential, machine learning in security is prone to subtle pitfalls that undermine its performance. We identify common pitfalls in the design, implementation, and evaluation of learning-based security systems. We propose actionable recommendations to support researchers in avoiding or mitigating the pitfalls where possible.
  arXiv  Detail & Related papers  (2020-10-19T13:09:31Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.