Abstract

This paper presents a Factor Graph based framework called AttackTagger for highly accurate and preemptive detection of attacks, i.e., before the system misuse. We use security logs on real incidents that occurred over a six-year period at the National Center for Supercomputing Applications (NCSA) to evaluate AttackTagger. Our data consist of security incidents that led to compromise of the target system, i.e., the attacks in the incidents were only identified after the fact by security analysts. AttackTagger detected 74 percent of attacks, and the majority them were detected before the system misuse. Finally, AttackTagger uncovered six hidden attacks that were not detected by intrusion detection systems during the incidents or by security analysts in post-incident forensic analysis.

Original languageEnglish (US)
Title of host publicationProceedings of the 2015 Symposium and Bootcamp on the Science of Security, HotSoS 2015
PublisherAssociation for Computing Machinery
ISBN (Electronic)9781450333764
DOIs
StatePublished - Apr 21 2015
EventSymposium and Bootcamp on the Science of Security, HotSoS 2015 - Urbana, United States
Duration: Apr 21 2015Apr 22 2015

Publication series

NameACM International Conference Proceeding Series
Volume21-22-April-2015

Other

OtherSymposium and Bootcamp on the Science of Security, HotSoS 2015
Country/TerritoryUnited States
CityUrbana
Period4/21/154/22/15

ASJC Scopus subject areas

  • Software
  • Human-Computer Interaction
  • Computer Vision and Pattern Recognition
  • Computer Networks and Communications

Fingerprint

Dive into the research topics of 'Preemptive intrusion detection: Theoretical framework and real-world measurements'. Together they form a unique fingerprint.

Cite this