| Title | Detecting an Alteration in Biometric Fingerprint Databases |
| Publication Type | Conference Paper |
| Year of Publication | 2018 |
| Authors | Shehu, Yahaya Isah, James, Anne, Palade, Vasile |
| Conference Name | Proceedings of the 2Nd International Conference on Digital Signal Processing |
| Publisher | ACM |
| Conference Location | New York, NY, USA |
| ISBN Number | 978-1-4503-6402-7 |
| Keywords | biometrics, composability, Fake fingerprints, fingerprints, Metrics, pubcrawl, Resiliency, signal processing security, support vector machine |
| Abstract | Assuring the integrity of biometric fingerprint templates in fingerprint databases is of paramount importance. Fingerprint templates contain a set of fingerprint minutiae which are various points of interest in a fingerprint. Most times, it is assumed that the stored biometric fingerprint templates are well protected and, as such, researchers are more concerned with improving/developing biometric systems that will not suffer from an unacceptable rate of false alarms and/or missed detections. The introduction of forensic techniques into biometrics for biometric template manipulation detection is of great importance and little research has been carried in this area. This paper investigates possible forensic techniques that could be used for stored biometric fingerprint templates tampering detection. A Support Vector Machine (SVM) classification approach is used for this task. The original and tampered templates are used to train the SVM classifier. The fingerprint datasets from the Biometrics Ideal Test (BIT) [13] are used for training and testing the classifier. Our proposed approach detects alterations with an accuracy of 90.5%. |
| URL | http://doi.acm.org/10.1145/3193025.3193029 |
| DOI | 10.1145/3193025.3193029 |
| Citation Key | shehu_detecting_2018 |
Detecting an Alteration in Biometric Fingerprint Databases