2026-09-19T18:39:44Z https://www.ideals.illinois.edu/oai-pmh

oai:www.ideals.illinois.edu:2142/78579 2023-07-11 col_2142_5131 col_2142_10761 com_2142_5130 com_2142_10755 com_2142_234

Iyer, Ravishankar K. Iyer, Ravishankar K Cao, Phuong 2015-07-22T22:32:41Z 2015-07-22T22:32:41Z 2017-07-23T09:15:21Z 2015-05 2015-01-23 This paper presents a factor graph based framework (named AttackTagger) for high accuracy and preemptive detection of attacks. We use security logs of real-incidents that occurred over a six-year period at the National Center for Supercomputing Applications (NCSA) at the University of Illinois to evaluate AttackTagger. Our data consist of attacks that led directly to the target system being compromised, i.e., not detected in advance, either by the security analysts or by intrusion detection systems. AttackTagger can detect 74 percent of attacks before the system misuse. AttackTagger uncovered six hidden attacks that were not detected by security analysts. Submission published under a 24 month embargo labeled 'U of I only', the embargo will last until 2017-05-01 The student, Phuong Cao, accepted the attached license on 2015-01-20 at 10:18. The student, Phuong Cao, submitted this Thesis for approval on 2015-01-20 at 10:35. This Thesis was approved for publication on 2015-01-23 at 15:27. DSpace SAF Submission Ingestion Package generated from Vireo submission #7689 on 2015-07-22 at 14:16:28 Made available in DSpace on 2015-07-22T22:32:41Z (GMT). No. of bitstreams: 2 cao_phuong123.pdf: 622872 bytes, checksum: 8c07b075e3b86bafb1744a1bef0d2d54 (MD5) license.txt: 4057 bytes, checksum: 08fe4bafa3625f947e1aacf6a4333a9e (MD5) Previous issue date: 2015-01-23 Embargo set by: Seth Robbins for item 79820 Lift date: 2017-07-22T22:34:16Z Reason: Author requested U of Illinois access only (OA after 2yrs) in Vireo ETD system U of I Only Restriction Lifted for Item 79820 on 2017-07-23T09:15:21Z. application/pdf http://hdl.handle.net/2142/78579 Copyright 2015 Phuong Cao probabilistic graphical models factor graph security incidents preemptive intrusion detection An experiment using factor graph for early attack detection text text 2015-5 Computer Science Computer Science University of Illinois at Urbana-Champaign Thesis M.S.