Resource Discovery: Using Network Traffic To Infer CPU And Memory Load

We argue that the network is actually an extension of the system unit; therefore we should be able to use network traffic generated by a node to ascertain the state of its various internal components. We demonstrate that this approach is feasible for passive resource discovery, and is also applicable to a variety of other resource characterization applications such as remote monitoring, and network intrusion detection.

Autorentext

Lanier has dual appointments at the Johns Hopkins University Applied Physics Laboratory and the JHU Information Security Institute. His research focus is network security. He holds a PhD in Computer Science, two MS degrees, and a BS degree. Also, he worked for over 10 years in industry (Ford Motor Company and AT&T). He is married and has 3 kids.