• Home
  • Search
  • MirrorFuzz: Leveraging LLM and Shared Bugs for Deep Learning Framework APIs Fuzzing
  • https://doi.org/10.1109/tse.2025.3619966Copy DOI Icon

MirrorFuzz: Leveraging LLM and Shared Bugs for Deep Learning Framework APIs Fuzzing

Show More
  • Abstract
  • Literature Map
  • References
  • Similar Papers
Abstract

Deep learning (DL) frameworks serve as the backbone for a wide range of artificial intelligence applications. However, bugs within DL frameworks can cascade into critical issues in higher-level applications, jeopardizing reliability and security. While numerous techniques have been proposed to detect bugs in DL frameworks, research exploring common API patterns across frameworks and the potential risks they entail remains limited. Notably, many DL frameworks expose similar APIs with overlapping input parameters and functionalities, rendering them vulnerable to shared bugs, where a flaw in one API may extend to analogous APIs in other frameworks. To address this challenge, we propose MirrorFuzz, an automated API fuzzing solution to discover shared bugs in DL frameworks. MirrorFuzz operates in three stages: First, MirrorFuzz collects historical bug data for each API within a DL framework to identify potentially buggy APIs. Second, it matches each buggy API in a specific framework with similar APIs within and across other DL frameworks. Third, it employs large language models (LLMs) to synthesize code for the API under test, leveraging the historical bug data of similar APIs to trigger analogous bugs across APIs. We implement MirrorFuzz and evaluate it on four popular DL frameworks (TensorFlow, PyTorch, OneFlow, and Jittor). Extensive evaluation demonstrates that MirrorFuzz improves code coverage by 39.92% and 98.20% compared to state-of-the-art methods on TensorFlow and PyTorch, respectively. Moreover, MirrorFuzz discovers 315 bugs, 262 of which are newly found, and 80 bugs are fixed, with 52 of these bugs assigned CNVD IDs.

Similar Papers
  • Research Article
  • Citations38

A comprehensive empirical study on bug characteristics of deep learning frameworks

  • Nov 01, 2022
  • Information and Software Technology
  • Yilin Yang +3
  • Research Article
  • Citations1

Improving Deep Learning Framework Testing with Model-Level Metamorphic Testing

  • Jun 22, 2025
  • Proceedings of the ACM on Software Engineering
  • Yanzhou Mu +8
  • Research Article

High-fidelity mechanical property confirmation of aluminum–agro-waste composites via integrated analytical, experimental, and deep learning framework

  • Apr 01, 2026
  • Next Materials
  • Stephen Ndubuisi Nnamchi +3
  • PDF
  • Research Article
  • Citations58

DLBench: a comprehensive experimental evaluation of deep learning frameworks

  • Feb 07, 2021
  • Cluster Computing
  • Radwa Elshawi +3
  • Conference Article
  • Citations50

Is using deep learning frameworks free?

  • Jun 27, 2020
  • Jiakun Liu +5
  • Research Article

Semantic Similarity Learning for Medical Literature: A Multimodal Framework Combining LLM and Deep Metric Learning

  • Apr 10, 2026
  • International Journal of Drug Delivery Technology
  • Deepika A +1
  • Research Article
  • Citations8

Transfer learning for fluence map prediction in adrenal stereotactic body radiation therapy

  • Dec 06, 2021
  • Physics in Medicine & Biology
  • Wentao Wang +8
  • Research Article
  • Citations28

Detection of moisture content in salted sea cucumbers by hyperspectral and low field nuclear magnetic resonance based on deep learning network framework

  • Mar 19, 2022
  • Food Research International
  • Fanyi Zeng +6
  • Research Article
  • Citations7

Image-based 3D reconstruction and permeability modelling of rock using enhanced interpretable deep residual learning

  • Jan 09, 2024
  • Engineering Analysis with Boundary Elements
  • Shan Lin +4
  • Research Article

Automated segmentation of the primary tumor in nasopharyngeal carcinoma using a deep learning framework in positron emission tomography imaging: a comparative study

  • Oct 23, 2025
  • Quantitative Imaging in Medicine and Surgery
  • Meina Liang +9
  • PDF
  • Research Article

TabDEG: Classifying differentially expressed genes from RNA-seq data based on feature extraction and deep learning framework.

  • Jul 22, 2024
  • PloS one
  • Sifan Feng +3
  • Research Article

Bridging Operator Semantic Inconsistencies: A Source-Level Cross-Framework Model Conversion Approach

  • Jun 19, 2025
  • Proceedings of the ACM on Software Engineering
  • Xingpei Li +7
  • Research Article
  • Citations65

A Novel Deep Learning Framework Based RNN-SAE for Fault Detection of Electrical Gas Generator

  • Jan 01, 2021
  • IEEE Access
  • Moath Alrifaey +2
  • Research Article
  • Citations100

A deep learning and novelty detection framework for rapid phenotyping in high-content screening.

  • Sep 27, 2017
  • Molecular Biology of the Cell
  • Christoph Sommer +3
  • Research Article
  • Citations17

Amplitude and phase estimations of power system harmonics using deep learning framework

  • Jul 09, 2020
  • IET Generation, Transmission & Distribution
  • Nagihan Severoglu +1
Cactus Communications logo

Copyright 2026 Cactus Communications. All rights reserved.