AI Test Infrastructure Capability for Department of Defense
Explore the UNCLASSIFIED program objectives focused on developing software to enhance AI test and evaluation processes to ensure effectiveness, robustness, and safety of AI-enabled systems within the Department of Defense. Learn about bridging the gap for transitioning existing AI T&E work into the DoD, increasing maturity, usability, and speed. Discover various products and tools developed for assessing AI models, generating visual predictions, and enhancing adversarial robustness in AI testing. Visit the provided link to access more information and current products.
Download Presentation
Please find below an Image/Link to download the presentation.
The content on the website is provided AS IS for your information and personal use only. It may not be sold, licensed, or shared on other websites without obtaining consent from the author. If you encounter any issues during the download, it is possible that the publisher has removed the file from their server.
You are allowed to download the files provided on this website for personal or commercial use, subject to the condition that they are used lawfully. All files are the property of their respective owners.
The content on the website is provided AS IS for your information and personal use only. It may not be sold, licensed, or shared on other websites without obtaining consent from the author.
E N D
Presentation Transcript
UNCLASSIFIED JATIC: Joint AI Test Infrastructure Capability DISTRIBUTION STATEMENT A Approved for public release; distribution is unlimited.
UNCLASSIFIED Program Objective Develop software to accelerate and enable AI test & evaluation (T&E) for Department of Defense In order to Provide insight on the effectiveness, robustness, and safety of the DoD s AI-enabled systems 2
UNCLASSIFIED Bridging the gap CDAO JATIC Transition existing AI T&E work into DoD by increasing maturity and usability Increase speed and rigor of AI T&E by providing common tools, standards, infrastructure Research & Engineering DoD Service PEOs, PMOs Huge interest and demand to employ AI Lack of knowledge, expertise, or centralized investment Rapid advancement of AI state of the art Research into advanced applications of AI for DoD- unique modalities
UNCLASSIFIED Products Name Description Developer Evaluate datasets for similarity, drift, and complexity ARiA DataEval Software test platform for assessing the trustworthy characteristics of AI models throughout development and deployment NIST Dioptra Generate visual saliency maps on AI predictions using black-box and white-box techniques Kitware Explainable AI Toolkit (XAITK) Develop standard model cards, data cards, and AI T&E reports in Powerpoint, directly from python MORSE Corp Gradient Hardened Extension of the Adversarial Robustness Toolbox (HEART) State-of-the-art library of adversarial attacks and defenses IBM A source of common types, protocols, and utilities to enable synergistic and streamlined AI T&E workflows MIT Lincoln Lab MAITE Evaluate models against physics-based, operationally-realistic perturbations Kitware Natural Robustness Toolkit (NRTK) Open-source AI & data science platform, designed for collaboration, scalability, and rapid deployment MetroStar & Quansight Nebari Visit us at https://cdao.pages.jatic.net/public to learn more and access our current products! 4
