Suggesting Alternatives for Potentially Insecure Artificial Intelligence Repositories: An Unsupervised Graph Embedding Approach

Simple item page
dc.contributor.authorLazarine, Ben
dc.contributor.authorSamtani, Sagar
dc.contributor.authorZhu, Hongyi
dc.contributor.authorVenkataraman, Ramesh
dc.date.accessioned2023-12-26T18:36:14Z
dc.date.available2023-12-26T18:36:14Z
dc.date.issued2024-01-03
dc.identifier.doihttps://doi.org/10.24251/HICSS.2024.066
dc.identifier.isbn978-0-9981331-7-1
dc.identifier.other447b079d-bb58-4334-9452-44cc47e2cfda
dc.identifier.urihttps://hdl.handle.net/10125/106441
dc.language.isoeng
dc.relation.ispartofProceedings of the 57th Hawaii International Conference on System Sciences
dc.rightsAttribution-NonCommercial-NoDerivatives 4.0 International
dc.rights.urihttps://creativecommons.org/licenses/by-nc-nd/4.0/
dc.subjectCybersecurity in the Age of Artificial Intelligence, AI for Cybersecurity, and Cybersecurity for AI
dc.subjectartificial intelligence
dc.subjectcybersecurity
dc.subjectopen-source software
dc.subjectunsupervised graph embedding
dc.titleSuggesting Alternatives for Potentially Insecure Artificial Intelligence Repositories: An Unsupervised Graph Embedding Approach
dc.typeConference Paper
dc.type.dcmiText
dcterms.abstractEmerging Artificial Intelligence (AI) applications are bringing with them both the potential for significant societal benefit and harm. Additionally, vulnerabilities within AI source code can make them susceptible to attacks ranging from stealing private data to stealing trained model parameters. Recently, with the adoption of open-source software (OSS) practices, the AI development community has introduced the potential to worsen the number of vulnerabilities present in emerging AI applications, building new applications on top of previous applications, naturally inheriting any vulnerabilities. With the AI OSS community growing rapidly to a scale that requires automated means of analysis for vulnerability management, we compare three categories of unsupervised graph embedding methods capable of generating repository embeddings that can be used to rank existing applications based on their functional similarity for AI developers. The resulting embeddings can be used to suggest alternatives to AI developers for potentially insecure AI repositories.
dcterms.extent9 pages
prism.startingpage548

Files

Original bundle

Now showing 1 - 1 of 1
Thumbnail Image
Name:
0054.pdf
Size:
960.07 KB
Format:
Adobe Portable Document Format
Download

Collections

Cybersecurity in the Age of Artificial Intelligence, AI for Cybersecurity, and Cybersecurity for AI