1 / 16

Enhancing Network Security with Meta-Session Aggregations and Cluster Analysis

This presentation provides an overview of network security strategies using meta-session aggregations and cluster analysis. Learn about network layout, event descriptions, OLAP support, scan detection, and more. Explore a sample application of identifying scans through clustering approaches. Gain insights into frequent and infrequent meta-sessions, cluster visualization, and drill-down operations.

Download Presentation

Enhancing Network Security with Meta-Session Aggregations and Cluster Analysis

An Image/Link below is provided (as is) to download presentation Download Policy: Content on the Website is provided to you AS IS for your information and personal use and may not be sold / licensed / shared on other websites without getting consent from its author. Content is provided to you AS IS for your information and personal use only. Download presentation by click this link. While downloading, if for some reason you are not able to download a presentation, the publisher may have deleted the file from their server. During download, if you can't get a presentation, the file might be deleted by the publisher.

E N D

Presentation Transcript


  1. SummarizingNetwork Security Data(presentation includes notes) Dave DeBarr debarr@mitre.org December 9, 2002

  2. Overview • Network Layout • Event Descriptions • OLAP Support • Meta-Session Aggregations • Scan Detection (a sample application) • Frequent Meta-Sessions • Infrequent Meta-Session Groupings • Cluster Analysis

  3. ACME Corporate Network Layout

  4. Event Descriptions

  5. Derived Attributes

  6. OLAP Visualization Example

  7. Meta-Session Aggregations

  8. Sample Application: Identifying Scans

  9. Scans: Clustering Approach • Agglomerative hierarchical clustering using Ward’s method to generate initial centroids • K-means for iterative relocation • Assigning each observation to the cluster for its nearest centroid • Recomputing the mean for each cluster • No concept of variance, but it’s quick  • Calinski-Harabasz index for evaluating models built using different values for K (the number of clusters)

  10. Scans: Heuristic-Based Density Estimation

  11. Summaries for 10 Common Scans

  12. Frequent Meta-Sessions

  13. Infrequent Meta-Session Groupings

  14. Cluster Prototypes for2:Drop:TCP/27374,3:TCP Connect:TCP/27374

  15. Cluster Visualization Example

  16. Tiers to Support Drill-Down Operations • Summary for all events • Summaries for inbound and outbound events • Summaries for frequent and infrequent meta-sessions • Summaries/prototypes for meta-session clusters • Summaries for meta-sessions • Lists of events for a particular meta-session

More Related