Technical Papers

Report on the First MBSynergy Workshop

July 24, 2025 • Technical Report

By Jerome Hugues, Will Hayes, Peter Capell, Nataliya Shevchenko

MBSynergy research focuses on ways of pursuing government equities using MBSE and digital engineering in DoD and IC settings; this report describes this team’s first working session.

DOWNLOAD mbsynergy research focuses on ways of pursuing government equities using mbse and digital engineering in dod and ic settings; this report describes this team’s first working session. Agile,Software Architecture,DevSecOps 2025

Software Bill of Materials (SBOM) Harmonization Plugfest 2024

July 17, 2025 • Special Report

By David Tobar, Jessie Jamieson, Jason Fricke, Sasank Vishnubhatla, Mark Priest

In this report, the authors describe the research findings and recommendations that resulted from the 2024 Software Bill of Materials (SBOM) Harmonization Plugfest research project.

DOWNLOAD in this report, the authors describe the research findings and recommendations that resulted from the 2024 software bill of materials (sbom) harmonization plugfest research project. Enterprise Risk and Resilience Management,Supply Chain Assurance 2025

What Can Generative AI Red-Teaming Learn from Cyber Red-Teaming?

July 16, 2025 • Technical Report

By Ellie Soto, Michael Feffer, Keltin Grimes, James Lucassen Anusha Sinha, Nathan M. VanHoudnos, Hoda Heidari

This paper investigates the applicability of established cyber red-teaming methodologies to the evaluation of generative AI systems, addressing the growing need for robust security assessments in AI-driven applications.

DOWNLOAD this paper investigates the applicability of established cyber red-teaming methodologies to the evaluation of generative ai systems, addressing the growing need for robust security assessments in ai-driven applications. Artificial Intelligence Engineering 2025

Practical Supervised Machine Learning Classification of Highly Imbalanced Text

May 22, 2025 • White Paper

By Austin Whisnant

In this paper, Austin Whisnant describes a machine learning model used to build a corpus of insider threat data to support insider threat research.

DOWNLOAD in this paper, austin whisnant describes a machine learning model used to build a corpus of insider threat data to support insider threat research. Insider Threat,Machine Learning 2025

Observational Human–AI (OHAI): A Defender Attribution Framework for Distinguishing Human vs. AI Threats

April 25, 2025 • White Paper

By Dustin D. Updyke, David Rossell, Shelly Fitzgerald

OHAI is a proposed framework for providing probabilistic human‑to‑autonomous attribution in cyber incidents.

DOWNLOAD ohai is a proposed framework for providing probabilistic human‑to‑autonomous attribution in cyber incidents. Situational Awareness,Measurement and Analysis,Cyber Workforce Development,Science of Cybersecurity,Incident Handling 2025

Kubernetes (k8s) in the Air Gap

April 15, 2025 • White Paper

By Maxwell Trdina, Matthew Heckathorn

This paper explains how the act of mirroring the required container images for a k8s deployment in the air gap has become increasingly simplified in the past few years.

DOWNLOAD this paper explains how the act of mirroring the required container images for a k8s deployment in the air gap has become increasingly simplified in the past few years. DevSecOps 2025

Center for Calibrated Trust Measurement and Evaluation (CaTE)—Guidebook for the Development and TEVV of LAWS to Promote Trustworthiness

April 11, 2025 • White Paper

By Daniel Justice, Tyler Brooks, Andrew O. Mellinger, Christopher Fairfax

This guidebook supports personnel in the development and testing of autonomous weapon systems that employ ML, focusing on system reliability and operator trust.

DOWNLOAD this guidebook supports personnel in the development and testing of autonomous weapon systems that employ ml, focusing on system reliability and operator trust. Artificial Intelligence Engineering,Artificial Intelligence 2025

Reference Architecture for Assuring Ethical Conduct in LAWS

April 11, 2025 • White Paper

By Eric Heim, Andrew O. Mellinger, Tyler Brooks, Andrew Schellenberg, Charles Loughin, Emily Newman

This reference architecture provides guidance to reason about designing and developing ML-enabled autonomous systems that have the capability to use lethal force.

DOWNLOAD this reference architecture provides guidance to reason about designing and developing ml-enabled autonomous systems that have the capability to use lethal force. Artificial Intelligence Engineering,Artificial Intelligence 2025

Key Takeaways from Zero Trust Industry Day 2024

April 3, 2025 • White Paper

By Patsy Bulisco, Rhonda Brown

This paper describes key takeaways from Zero Trust Industry Day 2024.

DOWNLOAD this paper describes key takeaways from zero trust industry day 2024. Zero Trust 2025

AI Hygiene Starts with Models and Data Loaders

March 13, 2025 • White Paper

By Matt Churilla, Shing-hon Lau, Mahmoud Shabana, Renae Metcalf

This paper places a call to action for traditional cybersecurity tools and techniques to be applied to artificial intelligence (AI) for improving the cybersecurity of AI systems.

DOWNLOAD this paper places a call to action for traditional cybersecurity tools and techniques to be applied to artificial intelligence (ai) for improving the cybersecurity of ai systems. Artificial Intelligence Engineering,Cybersecurity Engineering 2025