Python Fuzzing for Trustworthy Machine Learning Frameworks

Ilya Yegorov, Eli Kobrin, Darya Parygina, Alexey Vishnyakov, Andrey Fedotov
3/19/2024
cs.CRcs.AIcs.SE

No confident code implementation found for this paper. 5 possible matches can be shown below.

Abstract

Ensuring the security and reliability of machine learning frameworks is crucial for building trustworthy AI-based systems. Fuzzing, a popular technique in secure software development lifecycle (SSDLC), can be used to develop secure and robust software. Popular machine learning frameworks such as PyTorch and TensorFlow are complex and written in multiple programming languages including C/C++ and Python. We propose a dynamic analysis pipeline for Python projects using the Sydr-Fuzz toolset. Our pipeline includes fuzzing, corpus minimization, crash triaging, and coverage collection. Crash triaging and severity estimation are important steps to ensure that the most critical vulnerabilities are addressed promptly. Furthermore, the proposed pipeline is integrated in GitLab CI. To identify the most vulnerable parts of the machine learning frameworks, we analyze their potential attack surfaces and develop fuzz targets for PyTorch, TensorFlow, and related projects such as h5py. Applying our dynamic analysis pipeline to these targets, we were able to discover 3 new bugs and propose fixes for them.

View on arXivView PDF

Code Implementations

No confident code match yet

We couldn't find an author-owned or strongly-evidenced community implementation for this paper. 5 weaker matches are hidden by default — verify before relying on them.

No code implementations found yet.

Know of an implementation? Let us know in the comments below!

Similar Papers

LLbezpeky: Leveraging Large Language Models for Vulnerability Detection

87% match2024

AI for DevSecOps: A Landscape and Future Opportunities

83% match2024

Explaining the Contributing Factors for Vulnerability Detection in Machine Learning

83% match2024

On Security Weaknesses and Vulnerabilities in Deep Learning Systems

83% match1 repo42024

Adversarial Machine Learning: Attacks, Defenses, and Open Challenges

83% match2025

AutoSafeCoder: A Multi-Agent Framework for Securing LLM Code Generation through Static Analysis and Fuzz Testing

83% match1 repo282024

Cite this paper

@article{yegorov2024python,
  title  = {Python Fuzzing for Trustworthy Machine Learning Frameworks},
  author = {Ilya Yegorov and Eli Kobrin and Darya Parygina and Alexey Vishnyakov and Andrey Fedotov},
  year   = {2024},
  eprint = {2403.12723},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2403.12723v2}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2403.12723.svg)](https://codeofpaper.com/paper/2403.12723)

Discussion