SEI Digital Library
Latest Publications
A Preliminary Report on a Model for Maturing AI Adoption: From Hype to Achieving Repeatable, Predictable Outcomes
• Technical Report
This document introduces the key concepts of a model for AI adoption, which will provide organizational leaders with guidance on overcoming the challenges that arise as they try to realize …
Read
A Practitioner’s Guide to Designing and Developing Hands-On Cybersecurity Skilling Continuation Labs
• Technical Report
This report describes Skilling Continuation Labs that provide novel, relevant, and unique hands-on immersive training for the federal cybersecurity workforce.
Read
Orchestrating the Chaos: Protecting Wireless Networks from Cyber Attacks
• Podcast
This podcast explores radio frequency attacks, such as those conducted by APT28, and how software and cybersecurity play key roles in preventing and mitigating these exploitations.
Listen
DoD Work Sponsor User Guide
• User's Guide
The SEI is operated and managed by Carnegie Mellon University as a Federally Funded Research & Development Center. Sponsors fund the SEI's R&D efforts via this contract, which is administered …
Learn More
Non-DoD Work Sponsor User Guide
• User's Guide
The SEI is operated and managed by Carnegie Mellon University as a Federally Funded Research & Development Center. Sponsors fund the SEI's R&D efforts via this contract, which is administered …
Learn More
Bridging Research and Practice in LLM Agent Security
• White Paper
This systematic review discusses academic surveys, grey literature sources, and real-world case studies on securing LLM agents.
Read
From Data to Performance: Understanding and Improving Your AI Model
• Podcast
Drift in data and concept, evolving edge cases, and emerging phenomena can undermine the correlations that AI classifiers rely on. In this podcast, SEI researchers discuss a new tool to …
Listen
What Could Possibly Go Wrong? Safety Analysis for AI Systems
• Podcast
SEI researchers discuss their work on System Theoretic Process Analysis, or STPA, a hazard-analysis technique uniquely suitable for dealing with AI complexity when assuring AI systems.
Listen
How to Address the Problem of Poorly-Defined Requirements in Software System Design
• Webcast
In this webcast, Lori Flynn and Lyndsi Hughes offer a solution to the problem of poorly defined requirements in system design that can lead to software flaws, cost and time …
Watch
Getting Your Software Supply Chain In Tune with SBOM Harmonization
• Podcast
Software bills of materials or SBOMs are critical to software security and supply chain risk management. Regardless of the SBOM tool, the output should be consistent for a given piece …
Listen