Search Results

Abstract Letter from the Guest Editors

Abstract Threat identification and security analysis have become mandatory steps in the engineering design process of high-assurance systems, where successful cyberattacks can lead to hazardous property damage or loss of lives. This article describes a novel approach to perform security analysis on embedded systems modeled at the architectural level. The tool, called Security Threat Evaluation and Mitigation (STEM), associates threats from the Common Attack Pattern Enumeration and Classification (CAPEC) library with components and connections and suggests potential defense patterns from the National Institute of Standards and Technology (NIST) Special Publication (SP) 800-53 security standard. This article also provides an illustrative example based on a drone package delivery system modeled in AADL.

Abstract Fighter pilots must study models of aircraft dynamics before learning complex maneuvers and tactics. Similarly, autonomous fighter aircraft applications may benefit from a model-based learning approach. Instead of using a preexisting physics model of a given aircraft, a machine learning system can learn a predictive model of the aircraft physics from training data. Furthermore, it can model interactions between multiple friendly aircraft, enemy aircraft, and the environment. Such a system can also learn to represent state variables that are not directly observable, as well as dynamics that are not hard coded. Existing model-based methods use a deep neural network that takes observable state information and agent actions as input and provides predictions of future observations as output. The proposed method builds upon this approach by adding a residual feedforward skip connection from some of the inputs to all of the outputs of the deep neural network.

Abstract Autonomy is a key enabling factor in uncrewed aircraft system (UAS) and advanced air mobility (AAM) applications ranging from cargo delivery to structure inspection to passenger transport, across multiple sectors. In addition to guiding the UAS, autonomy will ensure that they stay safe in a large number of off-nominal situations without requiring the operator to intervene. While the addition of autonomy enables the safety case for the overall operation, there is a question as to how we can assure that the autonomy itself will work as intended. Specifically, we need assurable technical approaches, operational considerations, and a framework to develop, test, maintain, and improve these capabilities. We make the case that many of the key autonomy functions can be realized in the near term with readily assurable, even certifiable, design approaches and assurance methods, combined with risk mitigations and strategically defined concepts of operations.