Harnessing LLMs for Document-Guided Fuzzing of OpenCV Library

TL;DR

This paper presents VISTAFUZZ, a novel approach that leverages large language models to parse API documentation and systematically generate test inputs, effectively detecting new bugs in the OpenCV library.

Contribution

VISTAFUZZ introduces a document-guided fuzzing method using LLMs to improve bug detection in large software libraries like OpenCV.

Findings

Detected 17 new bugs in OpenCV APIs

Confirmed 10 bugs, with 5 fixed

Demonstrated effectiveness of LLM-guided fuzzing

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.