Nathan M. VanHoudnos
SEI CERT
Publications by Nathan M. VanHoudnos
-
Juneberry - Tutorial
March 22, 2022 • Presentation
Andrew O. MellingerNathan M. VanHoudnosNick Winski
Presented at Naval Applications of Machine Learning 2022, this tutorial reviews Juneberry, a reproducible research framework to build, maintain, and evaluate ML with declarative configs.
read -
Measuring Beyond Accuracy
March 21, 2022 • Conference Paper
Violet TurriRachel DzombakEric Heim
This paper was presented at the 2022 AAAI Spring Symposium on AI Engineering.
read -
Train but Verify: Towards Practical AI Robustness
November 07, 2021 • Presentation
Nathan M. VanHoudnos
Train, but Verify is an effort to develop an AI Engineering process to train AI systems to have specific robustness properties.
read -
Train but Verify: Towards Practical AI Robustness
November 05, 2021 • Video
Nathan M. VanHoudnos
This short video provides an introduction to a research topic presented at the SEI Research Review 2021.
watch -
Robust and Secure AI
June 25, 2021 • White Paper
Hollen BarmerRachel DzombakMatt Gaston
This white paper discusses Robust and Secure AI systems: AI systems that reliably operate at expected levels of performance, even when faced with uncertainty and in the presence of danger or threat.
read -
Managing Vulnerabilities in Machine Learning and Artificial Intelligence Systems
June 10, 2021 • Podcast
Nathan M. VanHoudnosJonathan SpringAllen D. Householder
Allen Householder, Jonathan Spring, and Nathan VanHoudnos discuss how to manage vulnerabilities in AI/ML systems.
learn more -
Train, but Verify: Towards Practical AI Robustness
December 15, 2020 • Video
Nathan M. VanHoudnosJon Helland
This presentation describes efforts to train AI systems to enforce at least two security policies and verify security by testing against realistic threat models.
watch -
Train, but Verify: Towards Practical AI Robustness
November 03, 2020 • Presentation
Nathan M. VanHoudnosJon Helland
This presentation describes efforts to train AI systems to enforce at least two security policies and verify security by testing against realistic threat models.
read -
Poster - Train, but Verify: Towards Practical AI Robustness
November 03, 2020 • Poster
Nathan M. VanHoudnosJon Helland
This presentation describes efforts to train AI systems to enforce at least two security policies and verify security by testing against realistic threat models.
read -
On Managing Vulnerabilities in AI/ML Systems
October 01, 2020 • Conference Paper
Jonathan SpringAllen D. HouseholderApril Galyardt
This paper explores how the current paradigm of vulnerability management might adapt to include machine learning systems.
read -
Comments on NISTIR 8269 (A Taxonomy and Terminology of Adversarial Machine Learning)
February 04, 2020 • White Paper
April GalyardtNathan M. VanHoudnosJonathan Spring
Feedback to the U.S. National Institute of Standards and Technology (NIST) about NIST IR 8269, a draft report detailing the proposed taxonomy and terminology of Adversarial Machine Learning (AML).
read -
Secure Your Code with AI and NLP
June 04, 2019 • Webinar
Eliezer KanalNathan M. VanHoudnos
In this talk, we discussed how a branch of artificial intelligence called Natural Language Processing, or NLP, is being applied to computer code.
watch -
Towards Security Defect Prediction with AI
October 23, 2018 • Poster
Nathan M. VanHoudnos
This poster describes research comparing a state-of-the-art AI system to existing static analysis approaches for defect prediction.
read -
Prioritizing Alerts from Multiple Static Analysis Tools, Using Classification Models
August 14, 2018 • Conference Paper
Lori FlynnWilliam SnavelyDavid Svoboda
This paper was accepted by the SQUADE workshop at ICSE 2018. It describes the development of several classification models for the prioritization of alerts produced by static analysis tools and how those models were tested for accuracy.
read -
Three Software Innovations that DoD Needs Now
May 18, 2018 • Webinar
Jeff BolengRobert SchielaSam Procter
Watch Jeff Boleng, Robert Schiela, Samuel Procter, Lena Pons, and Nathan VanHoudnos discuss "Three Software Innovations that DoD Needs Now".
watch -
The Critical Role of Positive Incentives for Reducing Insider Threats
December 15, 2016 • Technical Report
Andrew P. MooreJeff SavindaElizabeth A. Monaco
This report describes how positive incentives complement traditional practices to provide a better balance for organizations' insider threat programs.
read