All Projects
Filter by

Ensuring Machine Learning Models Meet System and Mission Requirements
Created April 18, 2025
The SEI’s Machine Learning Test and Evaluation is a one-of-a-kind framework to evaluate machine learning models from inception to deployment.
LEARN MORE
Automating Mismatch Detection in ML Systems
Created Oct. 1, 2022 • Updated April 11, 2025
Timely deployment of Machine Learning (ML) systems is vital for critical national security missions. The SEI’s TEC tool reduces problems that cause delay in the fielding of ML systems.
LEARN MORE
AISIRT Advances National Security with Secure AI
Created Nov. 10, 2023 • Updated March 26, 2025
The SEI created an AISIRT to ensure that the Department of Defense and other federal agencies develop, adopt, and use AI effectively and securely to safeguard the security of the nation.
LEARN MORE
SEI Solutions That Improve the DoD's Cyber Mission Readiness
Created March 21, 2025
The SEI develops tools that virtualize systems to deliver high-quality training and user performance validation to ensure cyber teams are ready to face ever-evolving threats and challenges.
LEARN MORE
Improving Disaster Response with the xView2 Challenge
Created July 22, 2020 • Updated March 17, 2025
The DoD’s Defense Innovation Unit, the SEI, and other organizations launched the xView2 Challenge to create accurate, efficient machine learning models that can advance disaster response. The competition resulted in xView2, a machine learning system that analyzes satellite imagery to classify damage to structures.
LEARN MORE
Automating Container Minimization for the Edge
Created Nov. 27, 2024 • Updated March 12, 2025
The SEI's Container Minimization Tool prunes and deduplicates files to reduce storage waste and software vulnerabilities in the resource-limited environment of the tactical edge.
LEARN MORE
Delivering “Virtual,” Real-World Experiences to Build Elite Cyber Teams
Created May 28, 2019 • Updated Feb. 28, 2025
The SEI CERT Division develops simulations that offer cyber operators a way to get the experience they need to perform at elite levels.
LEARN MORE
Internet of Things (IoT) Security Platform Can Improve Warfighter Resilience, Deliver Cost Savings
Created Oct. 1, 2019 • Updated Feb. 27, 2025
Internet of Things (IoT) devices can provide useful capabilities, but many have known security vulnerabilities that have been exploited by malicious actors. The SEI KalKi security platform leverages software-defined networking (SDN) and network function virtualization (NFV) to enable secure integration of IoT devices into Department of Defense DOD) networks, even devices that are not fully trusted or configurable. Such integration can improve warfighter resilience and deliver cost savings.
LEARN MORE
AI Trust Lab: Trustworthy AI for a Safer Nation
Created Oct. 31, 2019 • Updated Feb. 27, 2025
To support DoD mission success, the SEI’s Trust Lab advances the streamlined development of trustworthy and human-centered AI engineering practices by focusing on mission goals and prioritizing warfighter needs.
LEARN MORE
Connecting Securely to IoT Devices on the Battlefield
Created April 5, 2022 • Updated Feb. 24, 2025
The SEI developed new layers of security and functionality so that warfighters can securely access IoT devices on the battlefield.
LEARN MORE
Untangling the Knot: Enabling Rapid Software Evolution
Created Feb. 23, 2022 • Updated Oct. 3, 2024
Our automated refactoring solution recommends ways to refactor existing software, significantly increasing the efficiency of software evolution.
LEARN MORE
Automated Repair of Static Analysis Alerts (Redemption of False Positives)
Created Sept. 19, 2024
The SEI Redemption tool extensibly repairs code associated with static analysis alerts. Currently, it repairs uninitialized memory, null pointer, and other C/C++ weaknesses.
LEARN MORE
The Advanced Computing Lab
Created Sept. 3, 2024
The Advanced Computing Lab has extensive expertise in software performance optimization on diverse hardware architectures, and hardware and system design for software-based systems.
LEARN MORE
Artificial Intelligence Engineering Body of Knowledge
Created Oct. 4, 2022
AI Engineering focuses on developing tools, systems, and processes to enable the application of artificial intelligence in real-world contexts. The body of knowledge will be a standardization of this emergent discipline and will guide practitioners in implementing AI systems.
LEARN MORE
A Tool Set to Support Big Data Systems Acquisition
Created Sept. 28, 2017 • Updated Aug. 2, 2022
We offer an approach that reduces risk and simplifies the selection and acquisition of big data technologies when you acquire and develop big data systems.
LEARN MORE
DevSecOps Platform Independent Model (PIM)
Created May 26, 2022
The DevSecOps Platform Independent Model (PIM) enables organizations to implement DevSecOps in a secure, safe, and sustainable way in order to fully reap the benefits available from DevSecOps principles, practices, and tools.
LEARN MORE
Predicting Changing Conditions in Production Machine Learning Systems
Created May 20, 2022
The inference quality of deployed machine learning (ML) models degrades over time due to differences between training and production data, typically referred to as drift. The SEI developed a process and toolset for drift behavior analysis to better understand how models will react to drift before they are deployed and detect drift at runtime due to changing conditions.
LEARN MORE
AI Workforce Development
Created May 3, 2022
The SEI is advancing the professional discipline of AI engineering through the latest academic advancements at Carnegie Mellon University.
LEARN MORE
Helping the Army Deliver Secure, Cloud-Based Capabilities to the Warfighter
Created April 13, 2022
The SEI helped establish a roadmap for each phase of the product lifecycle so that the AEC can update its OT&E activities and support the Army’s move to the cloud.
LEARN MORE
Bringing Computation and Actionable Data to Battlefield Edge Environments
Created March 24, 2022
Making cloud computing resources available to military personnel in the field presents accessibility and security challenges. Tactical cloudlets provide secure, reliable, and timely access to cloud resources to help military personnel carry out their mission at the tactical edge despite unreliable connectivity to the cloud.
LEARN MORE
Juneberry
Created March 21, 2022
Juneberry automates the training, evaluation, and comparison of multiple ML models against multiple datasets. This makes the process of verifying and validating ML models more consistent and rigorous, which reduces errors, improves reproducibility, and facilitates integration.
LEARN MORE
Architecture Analysis and Design Language (AADL)
Created July 18, 2019 • Updated Feb. 2, 2022
Software for mission- and safety-critical systems, such as avionics systems in aircraft, is growing larger and more expensive. The Architecture Analysis and Design Language (AADL) addresses common problems in the development of these systems, such as mismatched assumptions about the physical system, computer hardware, software, and their interactions that can result in system problems detected too late in the development lifecycle.
LEARN MORE
Managing Technical Debt with Data-Driven Analysis
Created Sept. 28, 2017 • Updated Feb. 2, 2022
Most software projects carry technical debt. We develop tools and techniques that identify it and provide a complete view of the debt that you need to manage.
LEARN MORE
Architecting the Future of Software Engineering: A National Agenda for Software Engineering Research & Development
Created Nov. 3, 2021
This study identifies the technologies and areas of research that are most critical for enabling future software systems. The technology roadmap that resulted from this work is intended to guide the research efforts of the software engineering community toward future systems that are safe, predictable, and evolvable.
LEARN MORE
Characterizing and Detecting Mismatch in ML-Enabled Systems
Created July 7, 2021
The development of machine learning-enabled systems typically involves three separate workflows with three different perspectives—data scientists, software engineers, and operations. The mismatches that arise can result in failed systems. We developed a set of machine-readable descriptors for elements of ML-enabled systems to make stakeholder assumptions explicit and prevent mismatch.
LEARN MORE
Applying Causal Learning to Improve Software Cost Estimation and Project Control
Created March 16, 2021
SEI researchers have applied causal learning to help the Department of Defense identify factors that increase software costs and to provide guidance to control them.
LEARN MORE
AI Engineering: A National Initiative
Created Feb. 25, 2021
The SEI is taking the initiative to develop an AI engineering discipline that will lay the groundwork for establishing the practices, processes, and knowledge to build new generations of AI solutions.
LEARN MORE
Knowing When You Don’t Know: Engineering AI Systems in an Uncertain World
Created Feb. 17, 2021
This project is benchmarking methods for quantifying uncertainty in machine learning (ML) models. It is also developing techniques to identify the causes of uncertainty, rectify them, and efficiently update ML models to reduce uncertainty in their predictions.
LEARN MORE
Train, But Verify
Created Oct. 27, 2020
Attacks on machine learning (ML) systems can make them learn the wrong thing, do the wrong thing, or reveal sensitive information. Train, But Verify protects ML systems by training them to act against two of these threats at the same time and verifying them against realistic threat models.
LEARN MORE
Learning Patterns by Observing Behavior with Inverse Reinforcement Learning
Created Feb. 11, 2020
The Software Engineering Institute (SEI) uses Inverse Reinforcement Learning (IRL) techniques—an area of machine learning—to more efficiently and effectively teach novices how to perform expert tasks, achieve robotic control, and perform activity-based intelligence.
LEARN MORE
Community Guidance to Prevent Common Coding Errors
Created Dec. 1, 2017 • Updated Dec. 3, 2019
The SEI leads a community initiative to establish secure coding practices that prevent coding errors and that are reliable, usable, and effective.
LEARN MORE
Cyber Intelligence Study
Created May 14, 2019
The practice of cyber intelligence helps organizations protect their assets, know their risks, and recognize opportunities. In 2018, the SEI conducted a cyber intelligence study on behalf of the United States Office of the Director of National Intelligence (ODNI). Our task was to understand how organizations perform the work of cyber intelligence throughout the United States.
LEARN MORE
Training Army Analysts to Use the Big Data Platform
Created Jan. 4, 2019
ARCYBER is teaming with the SEI CERT Division to create training capabilities that help Army analysts develop the necessary skills for using its Big Data Platform.
LEARN MORE
Smart Grid Maturity Model (SGMM)
Created Sept. 11, 2018
The smart grid is a constantly evolving infrastructure of digital technology and power industry practices for improving the management of electricity generation, transmission, and distribution. The Smart Grid Maturity Model (SGMM) helps utilities plan their smart grid journeys.
LEARN MORE
Runtime Assurance for Big Data Systems
Created June 22, 2018
To help assure runtime performance in big data systems, we designed a reference architecture to automatically generate and insert monitors and aggregate metric streams.
LEARN MORE
SEI Hosts Crisis Simulation Exercise for Cyber Intelligence Research Consortium
Created Jan. 30, 2018
In SEI crisis simulation exercises, participants use scenarios that present fictitious malicious actors and environmental factors based on real-world events.
LEARN MORE
Cyber Lightning Case Study
Created Jan. 29, 2018
The SEI hosted Cyber Lightning, a three-day joint training exercise involving Air National Guard and Air Force Reserve units from western Pennsylvania and eastern Ohio.
LEARN MORE
USPS Case Study
Created Jan. 24, 2018
The SEI teamed with the U.S. Postal Service to help it improve its cybersecurity and resilience and collaborated on a program to develop a strong cybersecurity workforce.
LEARN MORE
Acquiring Systems, Not Just Software
Created Dec. 19, 2017
The U.S. Department of Defense (DoD) and federal agencies are increasingly acquiring software-intensive systems instead of building them with internal resources. However, acquisition programs frequently have difficulty identifying the critical software acquisition activities, deliverables, risks, and opportunities.
LEARN MORE
Digital Forensics: Advancing Solutions for Today's Escalating Cybercrime
Created Dec. 15, 2017
As cybercrime proliferates, CERT researchers help law enforcement investigators process digital evidence with courses, methodologies and tools, skills, and experience.
LEARN MORE
Helping Government Realize the Agile Advantage
Created Dec. 15, 2017
We develop a wealth of resources to help the U.S. Department of Defense (DoD) and federal agencies make informed decisions about using Agile and lean approaches in achieving their goals.
LEARN MORE
Security-Aware Acquisition
Created Dec. 15, 2017
The techniques developed by CERT researchers help you evaluate and manage cyber risk in today’s complex software supply chains.
LEARN MORE
Empirical Research Office
Created Dec. 15, 2017
We improve the capability delivered for every dollar of U.S. Department of Defense (DoD) investment made in software systems by improving the use of data in decision making.
LEARN MORE
System and Platform Evaluation
Created Dec. 15, 2017
CERT researchers develop and perform advanced penetration testing and cyber vulnerability assessments of organizations' systems and platforms.
LEARN MORE
Using Automation to Prioritize Alerts from Static Analysis Tools
Created Sept. 28, 2017
The new CERT method for validating and repairing defects found by static analysis tools helps auditors and coders address more alerts with less effort.
LEARN MORE
Supporting the U.S. Army's Joint Multi-Role Technology Demonstrator Effort
Created Sept. 28, 2017
We build and analyze virtual software systems to find problems early in development, before a system is built. Early discovery reduces cost and certification time.
LEARN MORE
Converting a Navy Weapon System from a 32- to a 64-Bit Architecture
Created Sept. 28, 2017
The SEI provided an independent assessment of the risks of migrating a weapons control system deployed by the U.S. Navy from one architecture to another.
LEARN MORE
GraphBLAS: A Programming Specification for Graph Analysis
Created Sept. 28, 2017
The GraphBLAS Forum is a world-wide consortium of researchers working to develop a programming specification for graph analysis that will simplify development.
LEARN MORE
Positive Incentives for Reducing Insider Threat
Created Sept. 28, 2017
Insiders present unique challenges to cybersecurity. We research insider threats and develop tools to analyze threat indicators in sociotechnical networks.
LEARN MORE
Improving Verification with Parallel Software Model Checking
Created Sept. 28, 2017
Current methods for software model checking can take too much time. We develop algorithms for SMC that execute many operations in parallel to improve scalability.
LEARN MORE
Design Pattern Recovery from Malware Binaries
Created Sept. 28, 2017
The U.S. Department of Defense (DoD) and industry face many malware problems. CERT researchers automate malware analysis capabilities, including those focused on malware family evolution and similarity.
LEARN MORE
Automating Vulnerability Discovery in Critical Applications
Created Sept. 28, 2017
CERT researchers develop automated tools that discover and mitigate software vulnerabilities and transfer them to researchers, procurement specialists, and software vendors.
LEARN MORE
QUELCE: Quantifying Uncertainty in Early Lifecycle Cost Estimation
Created Sept. 19, 2017
Costs for large new systems are hard to estimate. We developed a method to quantify uncertainty and increase confidence in a program's cost estimate.
LEARN MORE
Automated Code Repair
Created Sept. 19, 2017
Finding security flaws in source code is daunting; fixing them is an even greater challenge. Our researchers are creating automated tools that can repair bugs automatically or by prompting developers for more information to make effective repairs.
LEARN MORE
Verifying Distributed, Adaptive Real-Time (DART) Systems
Created Sept. 15, 2017
Distributed, adaptive real-time (DART) systems must satisfy safety-critical requirements. We developed a method to verify DART systems and generate assured code.
LEARN MORE
Explainable AI: Why Did the Robot Do That?
Created Sept. 15, 2017
To help human users trust their robot team members in critical situations, we develop tools that allow autonomous systems to explain their behavior.
LEARN MORE
Multi-Agent Decentralized Planning for Adversarial Robotic Teams
Created Sept. 15, 2017
We created multi-agent planning techniques, middleware, and algorithms that enable single users to manage fleets of UASs in real-world environments with changing adversaries.
LEARN MORE