A Geometric Framework for Unsupervised Anomaly Detection: Detecting Intrusions in Unlabeled Data

DMCA

A Geometric Framework for Unsupervised Anomaly Detection: Detecting Intrusions in Unlabeled Data (2002)

Cached

Download Links

by Eleazar Eskin , Andrew Arnold , Michael Prerau , Leonid Portnoy , Sal Stolfo

Venue:	Applications of Data Mining in Computer Security
Citations:	238 - 9 self

BibTeX

@INPROCEEDINGS{Eskin02ageometric,
    author = {Eleazar Eskin and Andrew Arnold and Michael Prerau and Leonid Portnoy and Sal Stolfo},
    title = {A Geometric Framework for Unsupervised Anomaly Detection: Detecting Intrusions in Unlabeled Data},
    booktitle = {Applications of Data Mining in Computer Security},
    year = {2002},
    publisher = {Kluwer}
}

OpenURL

Abstract

Abstract Most current intrusion detection systems employ signature-based methods or data mining-based methods which rely on labeled training data. This training data is typically expensive to produce. We present a new geometric framework for unsupervised anomaly detection, which are algorithms that are designed to process unlabeled data. In our framework, data elements are mapped to a feature space which is typically a vector space! d. Anomalies are detected by determining which points lies in sparse

Keyphrases

unlabeled data geometric framework anomaly detection feature space training data signature-based method labeled training data abstract current intrusion detection system new geometric framework unsupervised anomaly detection vector space data element data mining-based method

DMCA