LLM-HyPZ: Hardware Vulnerability Discovery using an LLM-Assisted Hybrid Platform for Zero-Shot Knowledge Extraction and Refinement

• URL: http://arxiv.org/abs/2509.00647v1
• Date: Sun, 31 Aug 2025 00:55:31 GMT
• Title: LLM-HyPZ: Hardware Vulnerability Discovery using an LLM-Assisted Hybrid Platform for Zero-Shot Knowledge Extraction and Refinement
• Authors: Yu-Zheng Lin, Sujan Ghimire, Abhiram Nandimandalam, Jonah Michael Camacho, Unnati Tripathi, Rony Macwan, Sicong Shao, Setareh Rafatirad, Rozhin Yasaei, Pratik Satam, Soheil Salehi,
• Abstract summary: LLM-HyPZ is a hybrid framework for zero-shot knowledge extraction and refinement from vulnerability corpora.<n>Applying LLM-HyPZ to the 2021-2024 CVE corpus (114,836 entries), we identified 1,742 hardware-related vulnerabilities.<n> Benchmarking across seven LLMs shows that LLaMA 3.3 70B achieves near-perfect classification accuracy (99.5%) on a curated validation set.
• Score: 2.128195197142326
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: The rapid growth of hardware vulnerabilities has created an urgent need for systematic and scalable analysis methods. Unlike software flaws, which are often patchable post-deployment, hardware weaknesses remain embedded across product lifecycles, posing persistent risks to processors, embedded devices, and IoT platforms. Existing efforts such as the MITRE CWE Hardware List (2021) relied on expert-driven Delphi surveys, which lack statistical rigor and introduce subjective bias, while large-scale data-driven foundations for hardware weaknesses have been largely absent. In this work, we propose LLM-HyPZ, an LLM-assisted hybrid framework for zero-shot knowledge extraction and refinement from vulnerability corpora. Our approach integrates zero-shot LLM classification, contextualized embeddings, unsupervised clustering, and prompt-driven summarization to mine hardware-related CVEs at scale. Applying LLM-HyPZ to the 2021-2024 CVE corpus (114,836 entries), we identified 1,742 hardware-related vulnerabilities. We distilled them into five recurring themes, including privilege escalation via firmware and BIOS, memory corruption in mobile and IoT systems, and physical access exploits. Benchmarking across seven LLMs shows that LLaMA 3.3 70B achieves near-perfect classification accuracy (99.5%) on a curated validation set. Beyond methodological contributions, our framework directly supported the MITRE CWE Most Important Hardware Weaknesses (MIHW) 2025 update by narrowing the candidate search space. Specifically, our pipeline surfaced 411 of the 1,026 CVEs used for downstream MIHW analysis, thereby reducing expert workload and accelerating evidence gathering. These results establish LLM-HyPZ as the first data-driven, scalable approach for systematically discovering hardware vulnerabilities, thereby bridging the gap between expert knowledge and real-world vulnerability evidence.

Related papers

• RealSec-bench: A Benchmark for Evaluating Secure Code Generation in Real-World Repositories [58.32028251925354]
  Large Language Models (LLMs) have demonstrated remarkable capabilities in code generation, but their proficiency in producing secure code remains a critical, under-explored area.<n>We introduce RealSec-bench, a new benchmark for secure code generation meticulously constructed from real-world, high-risk Java repositories.
  arXiv  Detail & Related papers  (2026-01-30T08:29:01Z)
• Why Does the LLM Stop Computing: An Empirical Study of User-Reported Failures in Open-Source LLMs [50.075587392477935]
  We conduct the first large-scale empirical study of 705 real-world failures from the open-source DeepSeek, Llama, and Qwen ecosystems.<n>Our analysis reveals a paradigm shift: white-box orchestration relocates the reliability bottleneck from model algorithmic defects to the systemic fragility of the deployment stack.
  arXiv  Detail & Related papers  (2026-01-20T06:42:56Z)
• CHASE: LLM Agents for Dissecting Malicious PyPI Packages [2.384873896423002]
  Large Language Models (LLMs) offer promising capabilities for automated code analysis.<n>Their application to security-critical malware detection faces fundamental challenges, including hallucination and context confusion.<n>We present CHASE, a high-reliability multi-agent architecture that addresses these limitations.
  arXiv  Detail & Related papers  (2026-01-11T10:06:14Z)
• An Empirical Evaluation of LLM-Based Approaches for Code Vulnerability Detection: RAG, SFT, and Dual-Agent Systems [1.5216960763930782]
  The rapid advancement of Large Language Models (LLMs) presents new opportunities for automated software vulnerability detection.<n>This paper presents a comparative study on the effectiveness of LLM-based techniques for detecting software vulnerabilities.
  arXiv  Detail & Related papers  (2026-01-01T08:05:51Z)
• Odysseus: Jailbreaking Commercial Multimodal LLM-integrated Systems via Dual Steganography [77.44136793431893]
  We propose a novel jailbreak paradigm that introduces dual steganography to covertly embed malicious queries into benign-looking images.<n>Our Odysseus successfully jailbreaks several pioneering and realistic MLLM-integrated systems, achieving up to 99% attack success rate.
  arXiv  Detail & Related papers  (2025-12-23T08:53:36Z)
• Detecting Vulnerabilities from Issue Reports for Internet-of-Things [0.0]
  We propose two approaches to detect vulnerability-indicating issues of 21 Eclipse IoT projects.<n>We fine-tune a pre-trained BERT Masked Language Model (MLM) on 11,000 GitHub issues for classifying vul.<n>Our contributions set the stage for accurately detecting IoT vulnerabilities from issue reports, similar to non-IoT systems.
  arXiv  Detail & Related papers  (2025-11-03T05:59:34Z)
• ParaVul: A Parallel Large Language Model and Retrieval-Augmented Framework for Smart Contract Vulnerability Detection [43.41293570032631]
  ParaVul is a retrieval-augmented framework to improve the reliability and accuracy of smart contract vulnerability detection.<n>We develop Sparse Low-Rank Adaptation (SLoRA) for LLM fine-tuning.<n>We construct a vulnerability contract dataset and develop a hybrid Retrieval-Augmented Generation (RAG) system.
  arXiv  Detail & Related papers  (2025-10-20T03:23:41Z)
• Why Not Act on What You Know? Unleashing Safety Potential of LLMs via Self-Aware Guard Enhancement [48.50995874445193]
  Large Language Models (LLMs) have shown impressive capabilities across various tasks but remain vulnerable to meticulously crafted jailbreak attacks.<n>We propose SAGE (Self-Aware Guard Enhancement), a training-free defense strategy designed to align LLMs' strong safety discrimination performance with their relatively weaker safety generation ability.
  arXiv  Detail & Related papers  (2025-05-17T15:54:52Z)
• AutoPatch: Multi-Agent Framework for Patching Real-World CVE Vulnerabilities [7.812032134834162]
  Large Language Models (LLMs) have emerged as promising tools in software development.<n>Their knowledge is limited to a fixed cutoff date, making them prone to generating code vulnerable to newly disclosed CVEs.<n>We propose AutoPatch, a framework designed to patch vulnerable LLM-generated code.
  arXiv  Detail & Related papers  (2025-05-07T07:49:05Z)
• Unveiling the Landscape of LLM Deployment in the Wild: An Empirical Study [7.5198516000202105]
  Large language models (LLMs) are increasingly deployed through open-source and commercial frameworks.<n>As LLM deployments become prevalent, particularly in industry, ensuring their secure and reliable operation has become a critical issue.<n>Insecure defaults and misconfigurations often expose LLM services to the public internet, posing serious security and system engineering risks.
  arXiv  Detail & Related papers  (2025-05-05T09:30:19Z)
• Adversarial Reasoning at Jailbreaking Time [49.70772424278124]
  Large language models (LLMs) are becoming more capable and widespread.<n>Recent advances in standardizing, measuring, and scaling test-time compute suggest new methodologies for optimizing models to achieve high performance on hard tasks.<n>In this paper, we apply these advances to the task of model jailbreaking: eliciting harmful responses from aligned LLMs.
  arXiv  Detail & Related papers  (2025-02-03T18:59:01Z)
• ADVLLM: Iterative Self-Tuning LLMs for Enhanced Jailbreaking Capabilities [63.603861880022954]
  We introduce ADV-LLM, an iterative self-tuning process that crafts adversarial LLMs with enhanced jailbreak ability.<n>Our framework significantly reduces the computational cost of generating adversarial suffixes while achieving nearly 100% ASR on various open-source LLMs.<n>It exhibits strong attack transferability to closed-source models, achieving 99% ASR on GPT-3.5 and 49% ASR on GPT-4, despite being optimized solely on Llama3.
  arXiv  Detail & Related papers  (2024-10-24T06:36:12Z)
• ProveRAG: Provenance-Driven Vulnerability Analysis with Automated Retrieval-Augmented LLMs [1.7191671053507043]
  Security analysts face the challenge of mitigating newly discovered vulnerabilities in real-time.<n>Over 300,000 Common Vulnerabilities and Exposures have been identified since 1999.<n>Over 25,000 vulnerabilities have been identified so far in 2024.
  arXiv  Detail & Related papers  (2024-10-22T20:28:57Z)
• Exploring Automatic Cryptographic API Misuse Detection in the Era of LLMs [60.32717556756674]
  This paper introduces a systematic evaluation framework to assess Large Language Models in detecting cryptographic misuses. Our in-depth analysis of 11,940 LLM-generated reports highlights that the inherent instabilities in LLMs can lead to over half of the reports being false positives. The optimized approach achieves a remarkable detection rate of nearly 90%, surpassing traditional methods and uncovering previously unknown misuses in established benchmarks.
  arXiv  Detail & Related papers  (2024-07-23T15:31:26Z)
• Understanding the Effectiveness of Large Language Models in Detecting Security Vulnerabilities [12.82645410161464]
  We evaluate the effectiveness of 16 pre-trained Large Language Models on 5,000 code samples from five diverse security datasets. Overall, LLMs show modest effectiveness in detecting vulnerabilities, obtaining an average accuracy of 62.8% and F1 score of 0.71 across datasets. We find that advanced prompting strategies that involve step-by-step analysis significantly improve performance of LLMs on real-world datasets in terms of F1 score (by upto 0.18 on average)
  arXiv  Detail & Related papers  (2023-11-16T13:17:20Z)

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.