The base-rate fallacy and the difficulty of intrusion detection
ACM Transactions on Information and System Security (TISSEC)
Neural network based intrusion detection system for critical infrastructures
IJCNN'09 Proceedings of the 2009 international joint conference on Neural Networks
Hi-index | 0.00 |
This paper describes a first investigation on a low cost and low false alarm, reliable mechanism for detecting manipulation of critical physical processes and falsification of system state. We call this novel mechanism Known Secure Sensor Measurements (KSSM). The method moves beyond analysis of network traffic and host based state information, in fact it uses physical measurements of the process being controlled to detect falsification of state. KSSM is intended to be incorporated into the design of new, resilient, cost effective critical infrastructure control systems. It can also be included in incremental upgrades of already installed systems for enhanced resilience. KSSM is based on known secure physical measurements for assessing the likelihood of an attack and will demonstrate a practical approach to creating, transmitting, and using the known secure measurements for detection.