Automatically detecting deceptive criminal identities

Gang Wang, Hsinchun Chen, Homa Atabakhsh

Research output: Contribution to journalReview articlepeer-review

78 Scopus citations


The uncovering patterns of criminal identity deception based on actual criminal records and algorithmic approach to reveal deceptive identities are discussed. The testing results shows that no false positive errors occurs which shows the effectiveness of the algorithm. The errors occurs in the false negative category in which unrelated suspects are recognized as being related. The threshold value is set to capture maximum possible true similar records. Adaptive threshold is required for making an automated process in the future research.

Original languageEnglish (US)
Pages (from-to)70-76
Number of pages7
JournalCommunications of the ACM
Issue number3
StatePublished - Mar 2004

ASJC Scopus subject areas

  • General Computer Science


Dive into the research topics of 'Automatically detecting deceptive criminal identities'. Together they form a unique fingerprint.

Cite this