High Efficiency Miniature Piezoelectric Motors

Not Available We propose to develop a unique system for the identification and management of strategic vulnerabilities that utilizes an innovative combination of artificial intelligence (AI) techniques. By drawing on our experience developing intrusion detection systems, statistical analysis tools, and model-based reasoning techniques, we propose to provide system administrators with a powerful unified risk management tool for heterogeneous networks of computers. In this task we draw inspiration from the success of automated medical diagnosis systems that utilize diverse diagnostic measures and an understanding of subsystem interactions in order to assess a patient's condition. In particular, our tool will detect and assess strategic vulnerabilities through the correlation of evidence from: COTS configuration examination applications, statistical analysis of previous incidents, intrusion detection techniques, and predictive analysis. The resulting system will be capable of accurately estimating the risks facing a network and identifying appropriate risk balancing measures. Finally, our system will be linked with our ICE intrusion detection system to facilitate the identification of previously unrecognized vulnerabilities and to provide continuous risk monitoring capability. The prototype tool developed in our Phase I effort will prove the feasibility of our approach and provide the basis for a complete Phase II implementation of SecureE(StratEgiC vUlneRability Evaluator).