Framework to Ensure and Assess Trustworthiness in Sensor Systems

Current trends suggest that in future concepts of operations a host of ubiquitous sensors will transparently provide ISR and decision support “on demand” to the warfighter without the need for tasking or querying individual sensors. Before this can happen, however, it is essential to significantly improve the reliability and trustworthiness of existing and envisioned sensor networks. During operations, the sensor network must be robust to deception, node compromise, and various other attacks, while maintaining the operator’s situational awareness regarding the health and integrity of the system. To address these needs, we propose a Framework to Ensure and Assess Trustworthiness in Sensor systems (FEATS) to identify attacks on sensor system integrity and inform the operator of sensor data trustworthiness. The framework provides for three critical functions: 1) attack detection via anomaly detection algorithms, including statistical rules and fixed-width clustering, 2) probabilistic threat assessment incorporating the current operational context using Bayesian belief networks, and 3) trust management provided by a human-system interface that uses meta-information visualization to portray the trustworthiness of critical sensor data.