http://hdl.handle.net/10125/20032 Tue, 18 Jun 2013 06:38:25 GMT 2013-06-18T06:38:25Z http://hdl.handle.net/10125/20512 Thesis (Ph.D.)--University of Hawaii at Manoa, 2008.; The NetTRIIAD prototype demonstrates a reduction in false positive detections and an improvement in positive predictive value, compared to that of a conventional misuse-based intrusion detection system. The prototype also demonstrates the capacity to detect novel threats. These results support the thesis that the hybrid model can overcome some of the limitations of other intrusion detection approaches. This research points to the usefulness of immune-inspired approaches for problems in the domain of information system security, and represents a step toward providing an immune system for self-protecting information systems.; This dissertation investigates a hybrid model for network threat detection that combines artificial immune system approaches with conventional intrusion detection methods. The research thesis asserts that a model combining artificial immune system and conventional methods can overcome limitations seen in conventional intrusion detection methods, such as false positive detections and difficulty adapting to novel threats. The Network Threat Recognition with Immune Inspired Anomaly Detection (NetTRIIAD) model presented here incorporates conventional intrusion detection and status monitoring methods as input for an artificial immune system based on the immunological Danger Model. This work details implementation of a prototype NetTRIIAD system and experimentation on a series of intrusion detection scenarios including both known and newly created threats.; This dissertation makes several contributions to knowledge in the areas of artificial immune systems and information system security. This work presents a novel methodology for applying artificial immune system techniques to a complex information system security problem. It also presents a working model for integrating artificial immune systems and conventional approaches to network threat detection. A further contribution is to the body of knowledge concerning the relatively new field of Danger Model inspired artificial immune systems and its application to solving complex problems.; Includes bibliographical references (leaves253-269).; Also available by subscription via World Wide Web; 268 leaves, bound 29 cm Tue, 01 Jan 2008 00:00:00 GMT http://hdl.handle.net/10125/20512 2008-01-01T00:00:00Z Fanelli, Robert L http://hdl.handle.net/10125/20511 Thesis (M.S.)--University of Hawaii at Manoa, 2007.; Includes bibliographical references (leaves 71-74).; xi, 74 leaves, bound ill. 29 cm Mon, 01 Jan 2007 00:00:00 GMT http://hdl.handle.net/10125/20511 2007-01-01T00:00:00Z Fujiwara, Kayo http://hdl.handle.net/10125/20510 Thesis (Ph.D.)--University of Hawaii at Manoa, 2008.; DNA microarray technology has provided researchers a high-throughput means to simultaneously measure expression levels for thousands of genes in an experiment. With a probit regression setting and assuming that the link function between significant gene expression data and latent variable for the response label is a Gaussian process, a kernel-induced hierarchical Bayesian framework is built for a cancer classification problem by using microarray gene expression data.; In summary, built on a Gaussian process model, a kernel-induced hierarchical Bayesian framework using microarray gene expression data for a cancer multi-classification problem is presented in this study. Our main contribution is a fully automated learning algorithm to solve this Bayesian model. Satisfactory results have been achieved in both the simulated examples and the real-world data studies.; Six published microarray datasets were analyzed in this study. The results show that predictive performance of our method for all these datasets is better than or at least as good as that of other state-of-the-art microarray analysis methods. Our method especially shows its superiority in analyzing one dataset that contains multiple suspicious mislabeled samples. For each of these datasets, we identified a set of significant genes, which can be used for further biological inspection at genome level.; Targeting a multi-classification problem and adopting a variable selection approach with a Gibbs sample as core, we developed the algorithm, kernel-imbedded Gaussian Process (KIGP), to analyze microarray data under a Bayesian framework. Through a feature projection procedure and using a univariate ranking scheme as gene-selection strategy, we further designed an alternative microarray analysis model, natural kernel-imbedded Gaussian Process (NKIGP). In the end, embedded with a reversible jump Markov chain Monte Carlo (RJMCMC) model, we present an efficient algorithm with a cascading structure to unify the proposed methods of this study.; The simulated examples demonstrate that, our method performs almost always close to the Bayesian bound in both the cases with linear Bayesian classifiers and the cases with very non-linear Bayesian classifiers. Even with mislabeled training samples, our method is still robust, showing its broad usability to those microarray analysis problems that linear methods may work flakily.; Includes bibliographical references (leaves xxx-xxx).; Also available by subscription via World Wide Web; 179 leaves, bound 29 cm Tue, 01 Jan 2008 00:00:00 GMT http://hdl.handle.net/10125/20510 2008-01-01T00:00:00Z Zhao, Xin