Open Daily: 10am - 10pm | Alley door pickup 10am - 7pm 3038 Hennepin Ave Minneapolis, MN
612-822-4611

  • Open Daily: 10am - 10pm
    Alley-side Pickup: 10am - 7pm

    3038 Hennepin Ave Minneapolis, MN
    612-822-4611

Open Daily: 10am - 10pm | Alley-side Pickup: 10am - 7pm
3038 Hennepin Ave Minneapolis, MN
612-822-4611
Holistic Network Defense: Fusing Host and Network Features for Attack Classification

Holistic Network Defense: Fusing Host and Network Features for Attack Classification

Ji, Jenny W.

Paperback

General EducationComputer Security

ISBN10: 1286862728
ISBN13: 9781286862728
Publisher: Biblioscholar
Published: Oct 26 2012
Pages: 124
Weight: 0.41
Height: 0.26 Width: 6.14 Depth: 9.21
Language: English

This work presents a hybrid network-host monitoring strategy, which fuses data from both the network and the host to recognize malware infections. This work focuses on three categories: Normal, Scanning, and Infected. The network-host sensor fusion is accomplished by extracting 248 features from network traffic using the Fullstats Network Feature generator and from the host using text mining, looking at the frequency of the 500 most common strings and analyzing them as word vectors. Improvements to detection performance are made by synergistically fusing network features obtained from IP packet flows and host features, obtained from text mining port, processor, logon information among others. In addition, the work compares three different machine learning algorithms and updates the script required to obtain network features. Hybrid method results outperformed host only classification by 31.7% and network only classification by 25%. The new approach also reduces the number of alerts while remaining accurate compared with the commercial IDS SNORT. These results make it such that even the most typical users could understand alert classification messages.

Also in

General Education

View All