Harnessing LLMs for Document-Guided Fuzzing of OpenCV Library

• URL: http://arxiv.org/abs/2507.14558v1
• Date: Sat, 19 Jul 2025 09:44:01 GMT
• Title: Harnessing LLMs for Document-Guided Fuzzing of OpenCV Library
• Authors: Bin Duan, Tarek Mahmud, Meiru Che, Yan Yan, Naipeng Dong, Dan Dongseong Kim, Guowei Yang,
• Abstract summary: VISTAFUZZ is a novel technique for harnessing large language models for document-guided fuzzing of the OpenCV library.<n>VISTAFUZZ extracts constraints on individual input parameters and dependencies between these.<n>We evaluate the effectiveness of VISTAFUZZ in testing 330 APIs in the OpenCV library, and the results show that VISTAFUZZ detected 17 new bugs, where 10 bugs have been confirmed, and 5 of these have been fixed.
• Score: 14.337352597473911
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: The combination of computer vision and artificial intelligence is fundamentally transforming a broad spectrum of industries by enabling machines to interpret and act upon visual data with high levels of accuracy. As the biggest and by far the most popular open-source computer vision library, OpenCV library provides an extensive suite of programming functions supporting real-time computer vision. Bugs in the OpenCV library can affect the downstream computer vision applications, and it is critical to ensure the reliability of the OpenCV library. This paper introduces VISTAFUZZ, a novel technique for harnessing large language models (LLMs) for document-guided fuzzing of the OpenCV library. VISTAFUZZ utilizes LLMs to parse API documentation and obtain standardized API information. Based on this standardized information, VISTAFUZZ extracts constraints on individual input parameters and dependencies between these. Using these constraints and dependencies, VISTAFUZZ then generates new input values to systematically test each target API. We evaluate the effectiveness of VISTAFUZZ in testing 330 APIs in the OpenCV library, and the results show that VISTAFUZZ detected 17 new bugs, where 10 bugs have been confirmed, and 5 of these have been fixed.

Related papers

• Your Fix Is My Exploit: Enabling Comprehensive DL Library API Fuzzing with Large Language Models [49.214291813478695]
  Deep learning (DL) libraries, widely used in AI applications, often contain vulnerabilities like overflows and use buffer-free errors.<n>Traditional fuzzing struggles with the complexity and API diversity of DL libraries.<n>We propose DFUZZ, an LLM-driven fuzzing approach for DL libraries.
  arXiv  Detail & Related papers  (2025-01-08T07:07:22Z)
• The Seeds of the FUTURE Sprout from History: Fuzzing for Unveiling Vulnerabilities in Prospective Deep-Learning Libraries [14.260990784121423]
  Future is the first universal fuzzing framework tailored for newly introduced and prospective DL libraries.<n>It uses historical bug information from existing libraries and fine-tunes LLMs for specialized code generation.<n>It significantly outperforms existing fuzzers in bug detection, success rate of bug reproduction, validity rate of code generation, and API coverage.
  arXiv  Detail & Related papers  (2024-12-02T09:33:28Z)
• ML-Bench: Evaluating Large Language Models and Agents for Machine Learning Tasks on Repository-Level Code [76.84199699772903]
  ML-Bench is a benchmark rooted in real-world programming applications that leverage existing code repositories to perform tasks. To evaluate both Large Language Models (LLMs) and AI agents, two setups are employed: ML-LLM-Bench for assessing LLMs' text-to-code conversion within a predefined deployment environment, and ML-Agent-Bench for testing autonomous agents in an end-to-end task execution within a Linux sandbox environment.
  arXiv  Detail & Related papers  (2023-11-16T12:03:21Z)
• Building an Open-Vocabulary Video CLIP Model with Better Architectures, Optimization and Data [102.0069667710562]
  This paper presents Open-VCLIP++, a framework that adapts CLIP to a strong zero-shot video classifier. We demonstrate that training Open-VCLIP++ is tantamount to continual learning with zero historical data. Our approach is evaluated on three widely used action recognition datasets.
  arXiv  Detail & Related papers  (2023-10-08T04:46:43Z)
• Private-Library-Oriented Code Generation with Large Language Models [52.73999698194344]
  This paper focuses on utilizing large language models (LLMs) for code generation in private libraries. We propose a novel framework that emulates the process of programmers writing private code. We create four private library benchmarks, including TorchDataEval, TorchDataComplexEval, MonkeyEval, and BeatNumEval.
  arXiv  Detail & Related papers  (2023-07-28T07:43:13Z)
• LibAUC: A Deep Learning Library for X-Risk Optimization [43.32145407575245]
  This paper introduces the award-winning deep learning (DL) library called LibAUC. LibAUC implements state-of-the-art algorithms towards optimizing a family of risk functions named X-risks.
  arXiv  Detail & Related papers  (2023-06-05T17:43:46Z)
• Do Not Take It for Granted: Comparing Open-Source Libraries for Software Development Effort Estimation [9.224578642189023]
  This paper aims at raising awareness of the differences incurred when using different Machine Learning (ML) libraries for software development effort estimation (SEE) We investigate 4 deterministic machine learners as provided by 3 of the most popular ML open-source libraries written in different languages (namely, Scikit-Learn, Caret and Weka) The results of our study reveal that the predictions provided by the 3 libraries differ in 95% of the cases on average across a total of 105 cases studied.
  arXiv  Detail & Related papers  (2022-07-04T20:06:40Z)
• Volkit: A Performance-Portable Computer Vision Library for 3D Volumetric Data [1.933681537640272]
  We present volkit, an open source library with high performance implementations of image manipulation and computer vision algorithms. We use volkit to process medical and simulation data that is rendered in VR and consequently integrated the library into the C++ virtual reality software CalVR.
  arXiv  Detail & Related papers  (2022-03-19T01:52:08Z)
• Multiple Object Trackers in OpenCV: A Benchmark [0.0]
  In this paper, we evaluate 7 trackers implemented in OpenCV against the MOT20 dataset. The results are shown based on Multiple Object Tracking Accuracy (MOTA) and Multiple Object Tracking Precision (MOTP) metrics.
  arXiv  Detail & Related papers  (2021-10-11T09:12:02Z)
• Captum: A unified and generic model interpretability library for PyTorch [49.72749684393332]
  We introduce a novel, unified, open-source model interpretability library for PyTorch. The library contains generic implementations of a number of gradient and perturbation-based attribution algorithms. It can be used for both classification and non-classification models.
  arXiv  Detail & Related papers  (2020-09-16T18:57:57Z)
• Applying Deep-Learning-Based Computer Vision to Wireless Communications: Methodologies, Opportunities, and Challenges [100.45137961106069]
  Deep learning (DL) has seen great success in the computer vision (CV) field. This article introduces ideas about applying DL-based CV in wireless communications.
  arXiv  Detail & Related papers  (2020-06-10T11:37:49Z)
• A DICOM Framework for Machine Learning Pipelines against Real-Time Radiology Images [50.222197963803644]
  Niffler is an integrated framework that enables the execution of machine learning pipelines at research clusters. Niffler uses the Digital Imaging and Communications in Medicine (DICOM) protocol to fetch and store imaging data. We present its architecture and three of its use cases: an inferior vena cava filter detection from the images in real-time, identification of scanner utilization, and scanner clock calibration.
  arXiv  Detail & Related papers  (2020-04-16T21:06:49Z)

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.