SEI Digital Library
Latest Publications
Breaking Down Barriers: How LLMs Enable Software Analysis in Classified Environments
• Podcast
This podcast explores the use of LLMs in unclassified environments to rapidly develop tools that accelerate software analysis in classified environments with improved accuracy.
ListenA Decade of GHOSTS in the Machine: From Cyber Range Realism to Cognitive Mission Rehearsal
• SEI Report
This paper describes how GHOSTS evolved from simple activity generation into a platform for simulating complex human, organizational, and machine behavior.
ReadSoftware-Defined Warfare: Expanding the Frontier
• Podcast
This podcast explores the evolution of software-defined warfare and the challenges of implementing software on the battlefield.
ListenUsing LLMs to Adjudicate Static-Analysis Alerts with Error Reduction Techniques
• Conference Paper
In this paper, the authors evaluate how well LLMs adjudicate static-analysis alerts, with and without error-reduction techniques, on three benchmarks: Juliet, FormAI, and SV-COMP.
ReadFrom Coordination Chaos to Mission Focus: The Waypoints Framework
• Podcast
This podcast explores the Waypoints Framework and how it can help teams visualize their work so they can own their processes.
ListenThe AI Adoption Maturity Model v1.0
• Book
Developed by the SEI in collaboration with Accenture, the AI Adoption Maturity Model enables organizations to create an assessment-based roadmap for successful AI adoption.
ReadAn LLM Evaluation Framework for High-Stakes AI
• Podcast
This podcast presents the Evaluation Large Language Models library, which turns evaluation from an ad-hoc process into a repeatable, extensible framework.
ListenBuilding Cyber Defenders of the Future: Curriculum Design for Emerging Roles
• Conference Paper
In this paper, the authors discuss developing hands-on curriculum for emerging Cyber Protection Team roles using learning engineering methods and open standards. This work was published by the European Conference …
ReadA Pointer-Ownership Model for C Inspired by Rust
• Conference Paper
In this paper, the authors present a new temporal memory safety model for C source code. This work was presented at the 7th ACM SIGPLAN Conference on Programming Language Design …
ReadRethinking and Maturing AI Adoption
• Webcast
Experts from the CMU SEI and Accenture share technical insights and lessons learned from maturing AI adoption in complex environments.
Watch