2021 Research Review
The CMU SEI Research Review 2021 virtual event spotlights recent, innovative research projects through a mix of technical presentations and conversations among CMU SEI subject matter experts and their collaborators working in sponsor, customer, and academic organizations.
Collaboration, an essential characteristic of the SEI as a federally funded research and development center (FFRDC), lies at the heart of everything you will see and hear at this event. It is the thread that ties together our work in research and development, piloting, transitioning, and policy input for the benefit of our sponsor and customers.
Our goal is to reduce the time required for this kind of architecture refactoring by two-thirds.
Read MoreAn automated conformance checker that can be integrated into the continuous integration workflow… This technology will correctly identify design nonconformances with precision greater than 90%.
Read MoreThe README research initiative is a strategic step forward towards a descriptive content generative process in modern DoD DevSecOps SDLCs.
Read MoreTo address AI/ML challenges, we propose to build on CMU’s Spiral technology, a hardware-software co-optimization.
Read MoreUG quantum computing has emerged as the quantum computing technology that can demonstrate not just quantum supremacy but also quantum advantage
Read MoreSAFIR will improve architecture-led safety assessment processes by delivering new tool-supported analysis and code generation capabilities to designers.
Read MoreAny timing failure can have disastrous consequences—an expected delay translating sensor data into actuation can cause system instability and loss of control.
Read MoreThe goal of Rapid Certifiable Trust is to reduce the deployment time of CPS by reducing the overall development and assurance times.
Read MoreOur solution focuses on development-compatible, implementation-level, protected, and verifiable execution building blocks that retrofit with existing code, incrementally, at a fine-granularity, with composability across multiple CHIC stack implementation layers.
Read MoreThis line of work, if successful, will enable the DoD to find and fix potential vulnerabilities in binary code that might otherwise be cost prohibitive to investigate or repair, thereby increasing the trustworthiness of fielded software
Read MoreThis research project will use machine learning and semantic analysis of data generated during CI/CD to reduce the number of alerts requiring human adjudication by 50%.
Read MoreThe ML system should neither do the wrong thing when presented with adversarial input nor reveal sensitive information about the training data during its operation.
Read MoreState-of-the-art ML models can produce inaccurate inferences in scenarios where humans would reasonably expect high accuracy.
Read MoreIn DoD systems, failure to recognize inference degradation can lead to costly reengineering, system decommissioning, and misinformed decisions.
Read More