Industries are now struggling with high level of security-risk vulnerabilities in their software environment which mainly originate from open-source dependencies. Industries’ percentage of open source in codebases is about 54% whereas ones with high security risks is about 30% (Synopsys 2018). While there are existing solutions for application security analysis, these typically only detect a limited subset of possible errors based on pre-defined rules. With the availability of open-source vulnerability resources, it is now possible to use data-driven techniques to discover vulnerabilities. Although there are a few AI-based solutions available, but there are some associated challenges: 1) use of artificial intelligence for application security (AppSec) towards vulnerability detection has been very limited and definitely not industry oriented, 2) the strategy to develop, use and manage such AppSec products in enterprises have not been investigated; therefore cybersecurity firms do not use even limited existing solutions. In this study, we aim to address these challenges with some strategies to develop such AppSec, their use management and economic values in enterprise environment.
Behfar, Stefan, "DEVELOPMENT STRATEGY AND MANAGEMENT OF AI-BASED VULNERABILITY DETECTION APPLICATIONS IN ENTERPRISE SOFTWARE ENVIRONMENT" (2023). ECIS 2023 Research-in-Progress Papers. 29.