In the fast-evolving landscape of cybersecurity, Large Language Models (LLMs) play a pivotal role, continually improving their ability to analyze software code. This paper introduces a novel approach to vulnerability scanning by integrating conservative SAST (Static Application Security Testing) scanners with LLM capabilities, resulting in the creation of LSAST (LLM-supported Static Application Security Testing). Our approach significantly enhances the performance of LLMs in vulnerability scanning, establishing a new standard in this field. We benchmark LSAST's efficiency and compare its results with a state-of-the-art LLM. Additionally, we address the inherent drawbacks of LLMs in vulnerability scanning: their reliance on static training datasets, which leads to the exclusion of the latest vulnerabilities, and the privacy concerns associated with sending code to third-party LLM providers. To mitigate these issues, we utilize an open-source LLM to ensure privacy and employ a novel approach to gather relevant vulnerability information, thereby equipping the LLM with up-to-date knowledge.
翻译:暂无翻译