DOE Patents title logo U.S. Department of Energy
Office of Scientific and Technical Information

Title: In-situ trainable intrusion detection system

Abstract

A computer implemented method detects intrusions using a computer by analyzing network traffic. The method includes a semi-supervised learning module connected to a network node. The learning module uses labeled and unlabeled data to train a semi-supervised machine learning sensor. The method records events that include a feature set made up of unauthorized intrusions and benign computer requests. The method identifies at least some of the benign computer requests that occur during the recording of the events while treating the remainder of the data as unlabeled. The method trains the semi-supervised learning module at the network node in-situ, such that the semi-supervised learning modules may identify malicious traffic without relying on specific rules, signatures, or anomaly detection.

Inventors:
; ; ;
Issue Date:
Research Org.:
Oak Ridge National Laboratory (ORNL), Oak Ridge, TN (United States)
Sponsoring Org.:
USDOE
OSTI Identifier:
1332095
Patent Number(s):
9497204
Application Number:
14/468,000
Assignee:
UT-Battelle, LLC (Oak Ridge, TN)
Patent Classifications (CPCs):
G - PHYSICS G06 - COMPUTING G06N - COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS
H - ELECTRICITY H04 - ELECTRIC COMMUNICATION TECHNIQUE H04L - TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
DOE Contract Number:  
AC05-00OR22725
Resource Type:
Patent
Resource Relation:
Patent File Date: 2014 Aug 25
Country of Publication:
United States
Language:
English
Subject:
97 MATHEMATICS AND COMPUTING; 99 GENERAL AND MISCELLANEOUS

Citation Formats

Symons, Christopher T., Beaver, Justin M., Gillen, Rob, and Potok, Thomas E.. In-situ trainable intrusion detection system. United States: N. p., 2016. Web.
Symons, Christopher T., Beaver, Justin M., Gillen, Rob, & Potok, Thomas E.. In-situ trainable intrusion detection system. United States.
Symons, Christopher T., Beaver, Justin M., Gillen, Rob, and Potok, Thomas E.. Tue . "In-situ trainable intrusion detection system". United States. https://www.osti.gov/servlets/purl/1332095.
@article{osti_1332095,
title = {In-situ trainable intrusion detection system},
author = {Symons, Christopher T. and Beaver, Justin M. and Gillen, Rob and Potok, Thomas E.},
abstractNote = {A computer implemented method detects intrusions using a computer by analyzing network traffic. The method includes a semi-supervised learning module connected to a network node. The learning module uses labeled and unlabeled data to train a semi-supervised machine learning sensor. The method records events that include a feature set made up of unauthorized intrusions and benign computer requests. The method identifies at least some of the benign computer requests that occur during the recording of the events while treating the remainder of the data as unlabeled. The method trains the semi-supervised learning module at the network node in-situ, such that the semi-supervised learning modules may identify malicious traffic without relying on specific rules, signatures, or anomaly detection.},
doi = {},
journal = {},
number = ,
volume = ,
place = {United States},
year = {2016},
month = {11}
}

Works referenced in this record:

Computer intrusion detection system and method based on application monitoring
patent, February 2007


Method and Apparatus for Automatic Online Detection and Classification of Anomalous Objects in a Data Stream
patent-application, August 2008