Pith. sign in

REVIEW 4 cited by

Fixing Hardware Security Bugs with Large Language Models

Not yet reviewed by Pith; the record is open.

Re-run · record.json Download PDF Read on arXiv ↗

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2302.01215 v1 pith:GCWKRTGL submitted 2023-02-02 cs.CR

Baleegh Ahmad , Shailja Thakur , Benjamin Tan , Ramesh Karri , Hammond Pearce This is my paper
classification cs.CR
keywords bugshardwarerepairframeworkllmssecuritylanguagedesign
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Novel AI-based code-writing Large Language Models (LLMs) such as OpenAI's Codex have demonstrated capabilities in many coding-adjacent domains. In this work we consider how LLMs maybe leveraged to automatically repair security relevant bugs present in hardware designs. We focus on bug repair in code written in the Hardware Description Language Verilog. For this study we build a corpus of domain-representative hardware security bugs. We then design and implement a framework to quantitatively evaluate the performance of any LLM tasked with fixing the specified bugs. The framework supports design space exploration of prompts (i.e., prompt engineering) and identifying the best parameters for the LLM. We show that an ensemble of LLMs can repair all ten of our benchmarks. This ensemble outperforms the state-of-the-art Cirfix hardware bug repair tool on its own suite of bugs. These results show that LLMs can repair hardware security bugs and the framework is an important step towards the ultimate goal of an automated end-to-end bug repair framework.

Discussion (0). Sign in to comment.

Forward citations

Cited by 4 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. Is Agentic AI Ready for Real-World Hardware Engineering? A Deep Dive with Phoenix-bench

    cs.AR 2026-05 unverdicted novelty 7.0 of 10

    Phoenix-bench shows agentic AI systems lose 37-58% resolved rate when moving from SWE-bench Verified to hardware tasks because bugs spread across parallel modules via signal flow, with testbench feedback lifting perfo...

  2. From Concept to Practice: an Automated LLM-aided UVM Machine for RTL Verification

    cs.AR 2025-04 conditional novelty 6.0 of 10

    UVM^2 is an LLM-driven system that generates and refines UVM testbenches for RTL verification, reporting up to substantial time savings and average code/function coverage of 87.44%/89.58% on designs up to 1.6K lines, ...

  3. Wit-HW: Bug Localization in Hardware Design Code via Witness Test Case Generation

    cs.AR 2025-08 unverdicted novelty 5.0 of 10

    Wit-HW generates witness test cases via mutation and uses spectrum-based comparison of passing and failing traces to rank buggy statements, reporting 49%, 73%, and 88% localization at Top-1, Top-5, and Top-10 across 41 bugs.

  4. VeriCWEty: Embedding enabled Line-Level CWE Detection in Verilog

    cs.AR 2026-04 unverdicted novelty 4.0 of 10

    VeriCWEty applies embedding-based analysis to detect CWEs in Verilog with 89% precision on examples like CWE-1244/1245 and 96% accuracy at line level.

Pith tools