Characterizing and Understanding Software Security Vulnerabilities in Machine Learning Libraries

Abstract

The application of machine learning (ML) libraries has been tremendously increased in many domains, including autonomous driving systems, medical, and critical industries. Vulnerabilities of such libraries could result in irreparable consequences. However, the characteristics of software security vulnerabilities have not been well studied. In this paper, to bridge this gap, we take the first step towards characterizing and understanding the security vulnerabilities of five well-known ML libraries, including TensorFlow, PyTorch, Scikit-learn, Pandas, and Numpy. To do so, we collected 596 security vulnerabilities to explore five major factors: 1) vulnerability types, 2) root causes, 3) symptoms, 4) fixing patterns, and 5) fixing efforts of security vulnerabilities in ML libraries. The findings of this study can help developers understand the characteristics of security vulnerabilities across different ML libraries. To make our finding actionable, we further developed DeepMut, an automated mutation testing tool, as a proof-of-concept application of our findings. DeepMut is designed to assess the adequacy of existing test suites of ML libraries against security-aware mutation operators extracted from the vulnerabilities studied in this work. We applied Deep-Mut on the TensorFlow kernel module and found more than 1k alive mutants not covered by the existing test suits, which have been confirmed by the development team of TensorFlow. The results demonstrate the usefulness of our findings.