Security and Authenticity of AI-generated code
Date
2023-10-20
Authors
Journal Title
Journal ISSN
Volume Title
Publisher
ORCID
Type
Thesis
Degree Level
Masters
Abstract
The intersection of security and plagiarism in the context of AI-generated code is a critical theme through-
out this study. While our research primarily focuses on evaluating the security aspects of AI-generated code,
it is imperative to recognize the interconnectedness of security and plagiarism concerns. On the one hand,
we do an extensive analysis of the security flaws that might be present in AI-generated code, with a focus
on code produced by ChatGPT and Bard. This analysis emphasizes the dangers that might occur if such
code is incorporated into software programs, especially if it has security weaknesses. This directly affects
developers, advising them to use caution when thinking about integrating AI-generated code to protect the
security of their applications. On the other hand, our research also covers code plagiarism. In the context
of AI-generated code, plagiarism, which is defined as the reuse of code without proper attribution or in
violation of license and copyright restrictions, becomes a significant concern. As open-source software and
AI language models proliferate, the risk of plagiarism in AI-generated code increases. Our research combines
code attribution techniques to identify the authors of AI-generated insecure code and identify where the code
originated. Our research emphasizes the multidimensional nature of AI-generated code and its wide-ranging
repercussions by addressing both security and plagiarism issues at the same time. This complete approach
adds to a more profound understanding of the problems and ethical implications associated with the use of
AI in code generation, embracing both security and authorship-related concerns.
Description
Keywords
Artificial Intelligence, AI-generated code, Common Weakness Enumeration(CWE), Common Vulnerabilities and Exposures, Plagiarism detection, Code attribution
Citation
Degree
Master of Science (M.Sc.)
Department
Computer Science
Program
Computer Science