An Overview of Large Language Model Approaches for Automated Software Vulnerability Detection

This article is licensed under the Creative Commons Attribution-NonCommercial 4.0 International License (CC BY-NC 4.0)

In the modern world, software security has become a top priority, as it directly determines the reliability of digital solutions and user trust. The growing number of cyber threats and the increasing complexity of software systems highlight the necessity of using effective tools for control and vulnerability prevention.

Traditional testing methods, such as static and dynamic analysis, remain important elements of security assurance; however, they face certain limitations in terms of speed, scalability, and completeness of vulnerability detection. These shortcomings drive the search for new approaches capable of enhancing existing solutions.

Advances in artificial intelligence methods open up new opportunities in software security. This includes not only the improvement or gradual replacement of traditional testing methods but also the introduction of fundamentally new approaches capable of preventing threats at early stages, as well as analyzing and prioritizing risks. Such solutions reduce the number of routine tasks and relieve security teams from excessive workloads, thereby increasing the overall efficiency and resilience of digital systems.

This article provides a review of the potential applications of AI-based methods in the context of software security. Their capabilities, limitations, and development prospects are analyzed. The findings indicate that integrating artificial intelligence into cybersecurity processes is a promising direction that requires further research to build more resilient and reliable software systems.