Framework to Ensure and Assess Trustworthiness in Sensor Systems (FEATS)

Current trends suggest that in future concepts of operations, 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 operators 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 unsupervised learning, 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 a sensor network. BENEFIT: We expect the full-scope Framework to Ensure and Assess Trustworthiness in Sensor Systems (FEATS) to have immediate and tangible benefits to both the federal government and the private sector. The sensor network attack detection and trust management tools developed under the proposed effort would be directly applicable to sensor security challenges in force protection, border security, health monitoring, industrial and building security, and emergency response.