Network intrusion detection

Mukherjee, Biswanath; Heberlein, L. Todd; Levitt, Karl N.

doi:10.1109/65.283931

Cited by 771 publications

(332 citation statements)

References 13 publications

Supporting

Mentioning

325

Contrasting

Unclassified

Order By: Relevance

“…, (x m , y m ), where x i ∈ R n is an input vector labeled by y i ∈ {+1, −1}. For many applications, such as network intrusion detection (Mukherjee et al 1994), disease diagnosis (Christodoulou and Pattichis 1999), handwritten character recognition (Veeramachaneni and Nagy 2005), and human face detection (Osuna et al 1997), data do appear in homogeneous groups. If the data structural information can be appropriately utilized to facilitate the classifier training, there will be a significant classification accuracy improvement.…”

Section: Introductionmentioning

confidence: 99%

Structured large margin machines: sensitive to data distributions

Yeung

Wang

et al. 2007

Mach Learn

View full text Add to dashboard Cite

This paper proposes a new large margin classifier-the structured large margin machine (SLMM)-that is sensitive to the structure of the data distribution. The SLMM approach incorporates the merits of "structured" learning models, such as radial basis function networks and Gaussian mixture models, with the advantages of "unstructured" large margin learning schemes, such as support vector machines and maxi-min margin machines. We derive the SLMM model from the concepts of "structured degree" and "homospace", based on an analysis of existing structured and unstructured learning models. Then, by using Ward's agglomerative hierarchical clustering on input data (or data mappings in the kernel space) to extract the underlying data structure, we formulate SLMM training as a sequential second order cone programming. Many promising features of the SLMM approach are illustrated, including its accuracy, scalability, extensibility, and noise tolerance. We also demonstrate the theoretical importance of the SLMM model by showing that it generalizes existing approaches, such as SVMs and M 4 s, provides novel insight into learning models, and lays a foundation for conceiving other "structured" classifiers.

show abstract

Section: Introductionmentioning

confidence: 99%

Structured large margin machines: sensitive to data distributions

Yeung

Wang

et al. 2007

Mach Learn

View full text Add to dashboard Cite

show abstract

“…While there are many applications based on group communication and topic-based pub/sub protocols such as information dissemination [17,22], a large variety of emerging applications benefit from the expressiveness, filtering, distributed event correlation, and complex event processing capabilities of content-based pub/sub. These applications include RSS feed filtering [31], stock-market monitoring engines [33], system and network management and monitoring [7,20], algorithmic trading with complex event processing [10,29], business process execution [32], business activity monitoring [7] and workflow management [5]. Typically, content-based pub/sub systems are built as application-level overlays of content-based pub/sub brokers, with publishing data sources and subscribing data sinks connecting to the broker overlay as clients.…”

Section: Introductionmentioning

confidence: 99%

Adaptive Content-Based Routing in General Overlay Topologies

Muthusamy

Jacobsen

2008

Middleware 2008

View full text Add to dashboard Cite

Abstract. This paper develops content-based publish/subscribe algorithms to support general overlay topologies, as opposed to traditional acyclic or tree-based topologies. Among other benefits, publication routes can adapt to dynamic conditions by choosing among alternate routing paths, and composite events can be detected at optimal points in the network. The algorithms are implemented in the PADRES publish/subscribe system and evaluated in a controlled local environment and a wide-area PlanetLab deployment. Atomic subscription notification delivery time improves by 20% in a well connected network, and composite subscriptions can be processed with 80% less network traffic and notifications delivered with about half the end to end delay.

show abstract

“…Among these, computer science has made significant advances with biologically inspired theories fitted in every branch. The typical bio-inspired systems are artificial neural networks, evolutionary computation, DNA computation, and now artificial immune systems (AIS) [2].…”

Section: Introductionmentioning

confidence: 99%

A Naturally Inspired Statistical Intrusion Detection Model

Mahboubian¹,

Udzir²

2013

IJCTE

View full text Add to dashboard Cite

Abstract-Growing interest in computational models based on natural phenomena with biologically inspired techniques in recent years have been tangible. The use of immune mechanisms in intrusion detection is promising. In [1] we proposed a new IDS model based on the Artificial Immune System (AIS) and a statistical approach. In this paper we are going to enhance that model in terms of detection speed and detection rate as well as overall overload. In contrast with the work in [1] here we do not use the concept of clonal selection and we use binary detector sets which leads to lower overload and therefore higher performance. The model is examined with DARPA data set which is famous among IDS researchers.Index Terms-Intrusion detection, artificial immune system, negative selection, data mining, network security.

show abstract

Network intrusion detection

Cited by 771 publications

References 13 publications

Structured large margin machines: sensitive to data distributions

Structured large margin machines: sensitive to data distributions

Adaptive Content-Based Routing in General Overlay Topologies

A Naturally Inspired Statistical Intrusion Detection Model

Contact Info

Product

Resources

About