Cyber maintenance policy optimization via adaptive learning
Y. Tan, and C. Xia. IEEE INFOCOM 2016 - The 35th Annual IEEE International Conference on Computer Communications, page 1-9. (April 2016)
DOI: 10.1109/INFOCOM.2016.7524522
Abstract
We develop a data-driven adaptive control framework to password management in cyber security systems. A password policy is the frontline of protection against cyber attacks, which contains a set of rules on password length, duration, etc. We assume password has censored lifetime, and policy maker determines the duration of the password without complete knowledge of its true lifetime distribution. We develop a gradient based algorithm integrated with a Bayesian learning framework. We show that our algorithm converges to optimal solution and adapts to non-stationary lifetime data.
%0 Conference Paper
%1 7524522
%A Tan, Y.
%A Xia, C. H.
%B IEEE INFOCOM 2016 - The 35th Annual IEEE International Conference on Computer Communications
%D 2016
%K security
%P 1-9
%R 10.1109/INFOCOM.2016.7524522
%T Cyber maintenance policy optimization via adaptive learning
%U http://ieeexplore.ieee.org/xpl/articleDetails.jsp?arnumber=7524522
%X We develop a data-driven adaptive control framework to password management in cyber security systems. A password policy is the frontline of protection against cyber attacks, which contains a set of rules on password length, duration, etc. We assume password has censored lifetime, and policy maker determines the duration of the password without complete knowledge of its true lifetime distribution. We develop a gradient based algorithm integrated with a Bayesian learning framework. We show that our algorithm converges to optimal solution and adapts to non-stationary lifetime data.
@inproceedings{7524522,
abstract = {We develop a data-driven adaptive control framework to password management in cyber security systems. A password policy is the frontline of protection against cyber attacks, which contains a set of rules on password length, duration, etc. We assume password has censored lifetime, and policy maker determines the duration of the password without complete knowledge of its true lifetime distribution. We develop a gradient based algorithm integrated with a Bayesian learning framework. We show that our algorithm converges to optimal solution and adapts to non-stationary lifetime data.},
added-at = {2016-08-16T11:06:52.000+0200},
author = {Tan, Y. and Xia, C. H.},
biburl = {https://www.bibsonomy.org/bibtex/2ee09b78d098c1efb4e37be443ed4f495/moch},
booktitle = {IEEE INFOCOM 2016 - The 35th Annual IEEE International Conference on Computer Communications},
doi = {10.1109/INFOCOM.2016.7524522},
interhash = {8b4a77cc0cc61fb29471ba1486e17a2c},
intrahash = {ee09b78d098c1efb4e37be443ed4f495},
keywords = {security},
month = {April},
pages = {1-9},
timestamp = {2016-08-16T11:06:52.000+0200},
title = {Cyber maintenance policy optimization via adaptive learning},
url = {http://ieeexplore.ieee.org/xpl/articleDetails.jsp?arnumber=7524522},
year = 2016
}