Grant: Alliance Grants
École de technologie supérieure
$25,000.00
Leveraging AI for early integration of software security in the DevOps pipeline
FY 2023-24
Summary
The goal of this proposal is to conduct initial research on how to leverage modern artificial intelligence models (e.g., Large Language Models) toward early detection of software security in the DevOps pipeline. Security is a critical component in developing modern software systems, yet a challenging topic that puts software systems and users' data at risk. While there is a long line of research on the topic of software security, there are still challenges that are not yet addressed in software security. Among these challenges is that software security issues are detected at a late stage of the development and releasing process (e.g., the DevOps process); identifying security issues requires a tremendous amount of time for reviewing source code changes and dependencies. On the other hand, the existing solutions, including those based on machine learning, often show low performances, these solutions' proposed security fixes are incomplete or too complex and require a large amount of effort to be considered. In this proposal, we first wish to conduct a preliminary study to identify to which extent modern artificial intelligence models (e.g., Large Language Models) can help improve the detection of software security issues at an early stage of the development of software systems.
Program
Alliance Grants
Recipient
Location
Quebec, Canada
Recipient Type
Academia
Type
Grant
Source
NSERC's Awards Data
As published
Application id
588572-2023
Name nom
Sayagh, Mohammed M
Department département
Génie logiciel et des TI
Organization id
53
Institution établissement
École de technologie supérieure
Province en
Québec
Province fr
Québec
Country en
CANADA
Country fr
CANADA
Fiscal year exercice financier
2023
Competition year année de concours
2023
Award amount
25000
Program id
ALLRP
Program name en
Alliance Grants
Program name fr
Subventions Alliance
Group en
RESEARCH PARTNERSHIPS
Group fr
PARTENARIATS DE RECHERCHE
Committee code
96
Committee name en
RPP Internal Decision Cttee
Committee name fr
Cté de décision interne - PPR
Area of application code
801
Area of application group en
Information and communication services
Area of application group fr
Services d'information et de télécommunications
Area of application en
Computer software
Area of application fr
Logiciel
Research subject code
9999
Research subject group en
Not available
Research subject group fr
Not available
Research subject en
Non disponible
Research subject fr
Non disponible
Application title
Leveraging AI for early integration of software security in the DevOps pipeline
Keyword
Artificial intelligence; DevSecOps; Empirical software engineering; Large Language Models; Software security
Application summary
The goal of this proposal is to conduct initial research on how to leverage modern artificial intelligence models (e.g., Large Language Models) toward early detection of software security in the DevOps pipeline. Security is a critical component in developing modern software systems, yet a challenging topic that puts software systems and users' data at risk. While there is a long line of research on the topic of software security, there are still challenges that are not yet addressed in software security. Among these challenges is that software security issues are detected at a late stage of the development and releasing process (e.g., the DevOps process); identifying security issues requires a tremendous amount of time for reviewing source code changes and dependencies. On the other hand, the existing solutions, including those based on machine learning, often show low performances, these solutions' proposed security fixes are incomplete or too complex and require a large amount of effort to be considered. In this proposal, we first wish to conduct a preliminary study to identify to which extent modern artificial intelligence models (e.g., Large Language Models) can help improve the detection of software security issues at an early stage of the development of software systems.