U.S. Air Force Sustainment Center

The rapid pace of technology change necessitates new approaches for upgrading and fielding high assurance mission systems in a timely manner. Furthermore, modern systems are often composed of multiple commercial or third-party components which must be implicitly trusted. We present an approach towards enabling rapid integration of components by employing an open system architecture that is not dependent on a trust relationship between third-party components. Our approach enables a system owner to enforce trust relationships between subsystems while taking advantage of the benefits of an open system architecture. In addition to enforcing trust, our approach allows third-party components to seamlessly interface with each other in an open system without the need to share their proprietary data. We further discuss the application of such an approach in an experimentation event and describe the benefits and limitations of adopting our approach.

This paper presents a method to directly generate inverse covariance matrices from correlated noise using generative machine learning techniques. This method uses convolution-based neural network structures to both infer correlation characteristics from noise and generate an appropriate inverse covariance matrix. Frobenius distance measurements were used to determine accuracy and consistency of the generated matrices. The goal of this work is to prove out a concept for adaptive filtering in detection with limited support samples. As such, proof of concept testing was performed to determine the feasibility of integrating this method with the well-known generalized likelihood ratio test (GLRT) algorithm. The testing demonstrated that the proposed method successfully generated the desired matrices and could be used to improve performance of detection algorithms with limited sample support. However, substantial work remains to improve this approach and determine how well it generalizes.