SEINA: A stealthy and effective internal attack in Hadoop systems

Jiayin Wang, Teng Wang, Zhengyu Yang, Ying Mao, Ningfang Mi, Bo Sheng

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

23 Scopus citations

Abstract

Big data processing frameworks such as Hadoop [1] are now widely adopted, however the security issues in large scale systems have not been well studied yet. Unlike prior work on data privacy and protection, this paper investigates a potential attack from a compromised internal node against the overall system performance. We develop an effective attack launched from the compromised node that can significantly degrade the data processing performance of the cluster without being detected and blacklisted for job execution, also present a mitigation scheme that protects a Hadoop system from such attack. The results of experiments show that this attack greatly slows down the job executions in the native Hadoop system even with some basic defense mechanisms, however, our mitigation schem can keep the whole cluster running efficiently under such attack.

Original languageEnglish
Title of host publication2017 International Conference on Computing, Networking and Communications, ICNC 2017
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages525-530
Number of pages6
ISBN (Electronic)9781509045884
DOIs
StatePublished - 10 Mar 2017
Event2017 International Conference on Computing, Networking and Communications, ICNC 2017 - Silicon Valley, United States
Duration: 26 Jan 201729 Jan 2017

Publication series

Name2017 International Conference on Computing, Networking and Communications, ICNC 2017

Other

Other2017 International Conference on Computing, Networking and Communications, ICNC 2017
Country/TerritoryUnited States
CitySilicon Valley
Period26/01/1729/01/17

Fingerprint

Dive into the research topics of 'SEINA: A stealthy and effective internal attack in Hadoop systems'. Together they form a unique fingerprint.

Cite this