—While transparent WDM optical networks become more and more popular as the basis of the Next Generation Internet (NGI) infrastructure, such networks raise many unique security issues. The existing protection schemes which only consider unintended failures and only rely on postmortem detection and reaction are not sufficient to provide security assurance for such infrastructures which require timely protection from malicious sabotage as well as inadvertent faults. Moreover, as may have been observed from past practices, providing a particular solution specialized to each incessantly discovered new problems would not dramatically improve the situation. In order to increase the security of future networks we will need to imbed intelligence into the network such that they can continuously learn from the experience in faults and self-organize to protect themselves from potential failures caused by malicious new attacks or ordinary reliability problems. In this paper, we present results ...
Jae-Seung Yeom, Ozan K. Tonguz, Gerardo A. Casta&n