Machine Learning for Source Code Vulnerability Detection: What Works and What Isn’t There Yet
Tina Marjanov, Ivan Pashchenko, Fabio Massacci
Abstract
We review machine learning approaches for detecting (and correcting) vulnerabilities in source code, finding that the biggest challenges ahead involve agreeing to a benchmark, increasing language and error type coverage, and using pipelines that do not flatten the code’s structure.
Topics & Concepts
Computer scienceBenchmark (surveying)Source codeCode (set theory)Vulnerability (computing)Open sourceProgramming languageArtificial intelligenceMachine learningComputer securityGeographySet (abstract data type)GeodesySoftwareSoftware Engineering ResearchSoftware Reliability and Analysis ResearchAdvanced Malware Detection Techniques