A novel detector for persistent spreads over data center based on bloom filter

Lin Han, Weijiang Liu, Zhiyang Li, Wenyu Qu, Mingqian Bai, Yegang Du

Research output: Contribution to journalArticlepeer-review

Abstract

Data center networks are vulnerable and easily plagued by long-term stealthy malicious attacks, which cannot be recognized by measurement based on host cardinality. Thus, this paper presents a novel detector for persistent spreads based on Bloom filter. In our design, multi-stage filter structure is proposed which can achieve high operation speed and low memory consumption because only filtered sips are calculated. Due to the nature of Bloom filter, false negative ratio (FNR) equals 0 all the time. The ideas and mechanisms are illustrated using different traces collected from real networks. Extensive experimental results based on real traces show that the proposed detector has better accuracy than other existing approaches.

Original languageEnglish
Pages (from-to)551-558
Number of pages8
JournalICIC Express Letters
Volume11
Issue number3
Publication statusPublished - 2017 Mar
Externally publishedYes

Keywords

  • Bloom filter
  • Cardinality estimation
  • Data center
  • Persistent spreads

ASJC Scopus subject areas

  • Control and Systems Engineering
  • Computer Science(all)

Fingerprint

Dive into the research topics of 'A novel detector for persistent spreads over data center based on bloom filter'. Together they form a unique fingerprint.

Cite this