LLMs to Adjudicate Static Analysis Alerts (LASAA) Assets
• Collection
Publisher
Software Engineering Institute
Abstract
Using large language models (LLMs) to adjudicate static analysis alerts enables more complete alert adjudication, reducing unknown risk and improving software security.
Software vulnerabilities pose a significant risk to critical systems. Static analysis is a standard method for evaluating source code, but it requires significant manual effort and is time consuming and expensive. LLMs are a new technology with promising initial results for automation of alert adjudication and rationales. Using LLMs to adjudicate static analysis alerts has the potential to enable more secure code, support mission effectiveness, and reduce support costs.
Collection Items
LLMs to Adjudicate Static Analysis Alerts (LASAA)
• Fact Sheet
By Software Engineering Institute
This fact sheet describes the LASAA project which uses large language models (LLMs) to adjudicate static analysis alerts. This enables more complete alert adjudication, reducing unknown risk and improving software …
Learn More
Secure Code Faster at Lower Cost for Ground and Space Systems: Techniques for High-Accuracy Static-Analysis Adjudication using LLMs
• Presentation
By William Klieber, Lori Flynn
Will Klieber and Lori Flynn presented this session at the Ground System Architectures Workshop on Tuesday, February 24, 2026.
Learn More
Automated Techniques for Ground Systems Software Security
• Poster
By Lori Flynn, William Klieber
Will Klieber and Lori Flynn presented this poster at the Ground System Architectures Workshop on Tuesday, February 24, 2026.
Download
Using Popular LLMs for Static Analysis Alert Adjudication: For the 2025 DoW AI/ML Technical Exchange Meeting
• Presentation
By Lori Flynn, William Klieber
On January 15, 2026, Lori Flynn and Will Klieber presented this session at the Department of War (DoW) Artificial Intelligence/Machine Learning (AI/ML) Technical Exchange Meeting, in the Security and Safety …
Learn More
Using LLMs to Adjudicate Static-Analysis Alerts
• Conference Paper
By William Klieber, Lori Flynn
This paper discusses techniques for using large language models to handle static analysis output.
Read
Evaluating Static Analysis Alerts with LLMs
• Blog Post
By William Klieber Lori Flynn
For safety-critical systems in areas such as defense and medical devices, software assurance is crucial. Analysts can use static analysis tools to evaluate source code without running it, allowing them …
Read
Using LLMs to Automate Static-Analysis Adjudication and Rationales
• Article
By Lori Flynn, William Klieber
This article discusses a model for using large language models (LLMs) to handle static analysis output.
Read