Traversal behavior k paths another type of behavior

Info icon This preview shows pages 74–77. Sign up to view the full content.

Traversal Behavior: k -Paths. Another type of behavior commonly seen in real attacks is that of attacker traversal, as depicted by the filled nodes and dotted edges in Figure 3.2, Step 3. To capture this behavior, we suggest the directed k -path . Informally, a k -path is a sequence of k edges where the destination node of the current edge in the sequence is the source node of the next edge in the sequence, and so on. In graph terms, a k -path is a directed subgraph where both size and diameter are equal to k (Kolaczyk, 2009). 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 74

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

Statistical Detection of Intruders Within Computer Networks 75 Fig. 3.3. Example out-star, centered at node v . The k -path captures the core of many network attacks, which have a path through the network with additional edges as “fuzz” around this core path. In addition, the k -path is limited to k edges, allowing for the detec- tion of very small anomalies. In the simulation (Section 3.5) and real-data (Section 3.6) studies, we choose to use 3-paths. 3-paths have the advantage of locality, but are also large enough to capture significant traversal. In a complete system, we forsee analyzing all 1-, 2- and 3-paths, but longer paths are less local, providing analysts with more alarmed edges to sort through. 3.1.4. Related work We are interested in testing the null hypothesis that all edges in the graph are behaving as they have historically, versus the alternative that there are local shapes of altered activity among the edges. To accomplish this goal, we have developed a method based on scan statistics to examine each of these shapes in the graph over sliding windows of time. Scan statistics have been widely used to detect local clusters of events (Naus, 1982; Loader, 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 75
76 J. Neil, C. Storlie, C. Hash and A. Brugh 1991; Kulldorff, 1997; Glaz et al. , 2001). The idea is to slide a window over a period of time and/or space, calculating a local deviation statistic. The most extreme of these is known as the scan statistic, which is used to decide if there is any deviation from historic behavior in the local window.
Image of page 76

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

Image of page 77
This is the end of the preview. Sign up to access the rest of the document.
  • Spring '12
  • Kushal Kanwar
  • Graph Theory, Statistical hypothesis testing, Imperial College Press, applicable copyright law

{[ 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