Skip to content
Sujan Ghimire
Research
Published

HWREx — Hardware Weakness and Vulnerability Exploration

A research framework that makes hardware vulnerability knowledge accessible through natural-language queries, semantic similarity, and LLM-assisted mitigation suggestions.

  • Research
  • AI/ML
  • Security Tools

Problem

Information about hardware weaknesses, vulnerabilities, and their mitigations is distributed across many records and is difficult for hardware designers and security engineers to search effectively.

Technical approach

  1. 01Accept natural-language queries describing a hardware design concern.
  2. 02Retrieve related hardware weakness and vulnerability records using semantic similarity.
  3. 03Present the associated risk information and mitigation guidance in an explorable, narrative form.
  4. 04Use large language models to assist with mitigation suggestions.

  1. 01

    Natural-language query

    Design or security concern

  2. 02

    Semantic retrieval

    Similarity over vulnerability records

  3. 03

    Risk exploration

    Related weaknesses & context

  4. 04

    Mitigation

    LLM-assisted suggestions

Figure. Conceptual overview of the HWREx workflow. Illustrative only; not a description of results.

My contributions

  • Lead author of the HWREx article in ACM Transactions on Design Automation of Electronic Systems (2025).
  • Co-author of the related LLM-HyPZ workshop paper on LLM-assisted hardware vulnerability discovery (IEEE ICDMW 2025).

Associated publications

IEEE ICDMW 2025Workshop

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

Yu-Zheng Lin, Sujan Ghimire, Abhiram Nandimandalam, Jonah Michael Camacho, Unnati Tripathi, Rony Macwan, Sicong Shao, Setareh Rafatirad, Rozhin Yasaei, Pratik Satam, Soheil Salehi

2025 IEEE International Conference on Data Mining Workshops (ICDMW), pp. 1268-1273, 2025.

DOI for LLM-HyPZ: Hardware Vulnerability Discovery Using an LLM-Assisted Hybrid Platform for Zero-Shot Knowledge Extraction and Refinement (opens in new tab)
ACM TODAESJournal

HWREx: AI-enabled Hardware Weakness and Risk Exploration and Storytelling Framework with LLM-assisted Mitigation Suggestion

Sujan Ghimire, Yu-Zheng Lin, Muntasir Mamun, Muhtasim Alam Chowdhury, Farhad Alemi, Shuyu Cai, Jinduo Guo, Mingyu Zhu, Honghui Li, Banafsheh Saber Latibari, Setareh Rafatirad, Pratik Satam, Soheil Salehi

ACM Transactions on Design Automation of Electronic Systems, vol. 30, no. 6, pp. 1-33, 2025.

DOI for HWREx: AI-enabled Hardware Weakness and Risk Exploration and Storytelling Framework with LLM-assisted Mitigation Suggestion (opens in new tab)