Allows us to develop solutions that are easily

Info icon This preview shows pages 35–37. Sign up to view the full content.

View Full Document Right Arrow Icon
allows us to develop solutions that are easily implemented and have certain optimality properties. However, AbIDSs and SbIDSs are clearly complementary, and neither alone is sufficient to detect and isolate the anomalies generated by attacks or non-malicious events. The reason is that both these types of IDSs, when working independently, are plagued by a high rate of false positives and are susceptible to carefully crafted attacks that “blend” themselves into normal traffic. The ability of changepoint detection techniques to run at high speeds and with small detection delays presents an interesting opportunity. What if one could combine these techniques with signature-type methods that offer very low FAR but are too heavy to use at line speeds? Do such synergistic IDSs exist, and if so, how can they be integrated? Such an approach is explored in this chapter. The main idea is to inte- grate two substantially different detection techniques – anomaly change- point detection-based methods and signature–spectral detection techniques. We demonstrate that the resulting hybrid anomaly–signature IDS is syn- ergistic and performs better than any individual system. More specifi- cally, the resulting IDS is based on a two-stage (cascade) hybrid approach that combines changepoint AbIDS and “flow-based” SbIDS to simultane- ously improve detection performance and lower FAR. This two-stage hybrid approach allows augmenting hard detection decisions with profiles that can be used for further analysis, e.g., for filtering false positives and confirming real attacks both at single-sensor and network levels. The hybrid IDS is tested on real attacks, and the results demonstrate the benefits of carefully combining anomaly and signature IDSs. Copyright © 2014. Imperial College Press. All rights reserved. May not be reproduced in any form without permission from the publisher, except fair uses permitted under U.S. or applicable copyright law. EBSCO Publishing : eBook Collection (EBSCOhost) - printed on 2/16/2016 3:37 AM via CGC-GROUP OF COLLEGES (GHARUAN) AN: 779681 ; Heard, Nicholas, Adams, Niall M..; Data Analysis for Network Cyber-security Account: ns224671
Image of page 35

Info iconThis preview has intentionally blurred sections. Sign up to view the full version.

View Full Document Right Arrow Icon
36 A. G. Tartakovsky The chapter is organized as follows. In Section 2.2 we outline certain theoretical aspects of quickest detection methods. In Section 2.3 we tran- sition from changepoint detection theory to cyber-security and formulate the principles of the anomaly IDS. In Section 2.4 we describe the novel hybrid anomaly–signature IDS that integrates anomaly- and signature- based detection systems and allows for efficient false alarm filtering and true attack confirmation. In Subsections 2.3.2 and 2.4.2 we present the results of experimental studies for real-world data with several challenging attacks.
Image of page 36
Image of page 37
This is the end of the preview. Sign up to access the rest of the document.

{[ snackBarMessage ]}

What students are saying

  • Left Quote Icon

    As a current student on this bumpy collegiate pathway, I stumbled upon Course Hero, where I can find study resources for nearly all my courses, get online help from tutors 24/7, and even share my old projects, papers, and lecture notes with other students.

    Student Picture

    Kiran Temple University Fox School of Business ‘17, Course Hero Intern

  • Left Quote Icon

    I cannot even describe how much Course Hero helped me this summer. It’s truly become something I can always rely on and help me. In the end, I was not only able to survive summer classes, but I was able to thrive thanks to Course Hero.

    Student Picture

    Dana University of Pennsylvania ‘17, Course Hero Intern

  • Left Quote Icon

    The ability to access any university’s resources through Course Hero proved invaluable in my case. I was behind on Tulane coursework and actually used UCLA’s materials to help me move forward and get everything together on time.

    Student Picture

    Jill Tulane University ‘16, Course Hero Intern