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

Title: Extracting dependencies between network assets using deep learning

Abstract

A network analysis tool receives network flow information and uses deep learning—machine learning that models high-level abstractions in the network flow information—to identify dependencies between network assets. Based on the identified dependencies, the network analysis tool can discover functional relationships between network assets. For example, a network analysis tool receives network flow information, identifies dependencies between multiple network assets based on evaluation of the network flow information, and outputs results of the identification of the dependencies. When evaluating the network flow information, the network analysis tool can pre-process the network flow information to produce input vectors, use deep learning to extract patterns in the input vectors, and then determine dependencies based on the extracted patterns. The network analysis tool can repeat this process so as to update an assessment of the dependencies between network assets on a near real-time basis.

Inventors:
; ; ; ; ; ;
Issue Date:
Research Org.:
Pacific Northwest National Lab. (PNNL), Richland, WA (United States)
Sponsoring Org.:
USDOE
OSTI Identifier:
1771624
Patent Number(s):
10833954
Application Number:
14/548,159
Assignee:
Battelle Memorial Institute (Richland, WA)
Patent Classifications (CPCs):
H - ELECTRICITY H04 - ELECTRIC COMMUNICATION TECHNIQUE H04L - TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
DOE Contract Number:  
AC05-76RL01830
Resource Type:
Patent
Resource Relation:
Patent File Date: 11/19/2014
Country of Publication:
United States
Language:
English

Citation Formats

Carroll, Thomas E., Chikkagoudar, Satish, Edgar, Thomas W., Oler, Kiri J., Arthur, Kristine M., Johnson, Daniel M., and Kangas, Lars J. Extracting dependencies between network assets using deep learning. United States: N. p., 2020. Web.
Carroll, Thomas E., Chikkagoudar, Satish, Edgar, Thomas W., Oler, Kiri J., Arthur, Kristine M., Johnson, Daniel M., & Kangas, Lars J. Extracting dependencies between network assets using deep learning. United States.
Carroll, Thomas E., Chikkagoudar, Satish, Edgar, Thomas W., Oler, Kiri J., Arthur, Kristine M., Johnson, Daniel M., and Kangas, Lars J. Tue . "Extracting dependencies between network assets using deep learning". United States. https://www.osti.gov/servlets/purl/1771624.
@article{osti_1771624,
title = {Extracting dependencies between network assets using deep learning},
author = {Carroll, Thomas E. and Chikkagoudar, Satish and Edgar, Thomas W. and Oler, Kiri J. and Arthur, Kristine M. and Johnson, Daniel M. and Kangas, Lars J.},
abstractNote = {A network analysis tool receives network flow information and uses deep learning—machine learning that models high-level abstractions in the network flow information—to identify dependencies between network assets. Based on the identified dependencies, the network analysis tool can discover functional relationships between network assets. For example, a network analysis tool receives network flow information, identifies dependencies between multiple network assets based on evaluation of the network flow information, and outputs results of the identification of the dependencies. When evaluating the network flow information, the network analysis tool can pre-process the network flow information to produce input vectors, use deep learning to extract patterns in the input vectors, and then determine dependencies based on the extracted patterns. The network analysis tool can repeat this process so as to update an assessment of the dependencies between network assets on a near real-time basis.},
doi = {},
journal = {},
number = ,
volume = ,
place = {United States},
year = {2020},
month = {11}
}

Works referenced in this record:

Method of and device for moving image contour recognition
patent, April 1992


Topology discovery for large ethernet networks
conference, January 2001

  • Lowekamp, Bruce; O'Hallaron, David; Gross, Thomas
  • Proceedings of the 2001 conference on Applications, technologies, architectures, and protocols for computer communications - SIGCOMM '01
  • https://doi.org/10.1145/383059.383078

WAP5: black-box performance debugging for wide-area systems
conference, January 2006


A supervised machine learning approach to classify host roles on line using sFlow
conference, January 2013


Flow classification using clustering and association rule mining
conference, December 2010

  • Chaudhary, Umang K.; Papapanagiotou, Ioannis; Devetsikiotis, Michael
  • 2010 IEEE 15th International Workshop on Computer Aided Modeling and Design of Communication Links and Networks (CAMAD), 2010 15th IEEE International Workshop on Computer Aided Modeling, Analysis and Design of Communication Links and Networks (CAMAD)
  • https://doi.org/10.1109/CAMAD.2010.5686959

Macroscope: end-point approach to networked application dependency discovery
conference, January 2009

  • Popa, Lucian; Chun, Byung-Gon; Stoica, Ion
  • Proceedings of the 5th international conference on Emerging networking experiments and technologies - CoNEXT '09
  • https://doi.org/10.1145/1658939.1658966

Dependency Analysis in Distributed Systems using Fault Injection: Application to Problem Determination in an e-commerce Environment
conference, January 2001

  • Bagchi, Saurabh; Kar, Gautam; Hellerstein, Joe
  • 12th International Workshop on Distributed Systems: Operations & Management, Operations & Management : 12th International Workshop on Distributed Systems, DSOM 2001, Nancy, France, October 15-17, 2001: Proceedings
  • https://doi.org/10.3990/2.14

Security informatics research challenges for mitigating cyber friendly fire
journal, September 2014


Towards highly reliable enterprise network services via inference of multi-level dependencies
journal, October 2007


Performance debugging for distributed systems of black boxes
journal, December 2003


What's going on?: learning communication rules in edge networks
journal, October 2008