2020/07/07 by Roberto Casula, Casula, Roberto, Giulia Orrù +9
Biochemistry, Genetics and Molecular Biology · Computer Science · Social Sciences · #Biometric Identification and Security #Computer Vision and Pattern Recognition (cs.CV) #FOS: Computer and information sciences #Forensic Fingerprint Detection Methods #Forensic and Genetic Research
paper · pdf · doi:10.48550/arxiv.2007.03397
openalex publication_date 2020/07/07 · openalex created_date 2022/07/26 · openalex updated_date 2026/07/28
We investigated the threat level of realistic attacks using latent\nfingerprints against sensors equipped with state-of-art liveness detectors and\nfingerprint verification systems which integrate such liveness algorithms. To\nthe best of our knowledge, only a previous investigation was done with spoofs\nfrom latent prints. In this paper, we focus on using snapshot pictures of\nlatent fingerprints. These pictures provide molds, that allows, after some\ndigital processing, to fabricate high-quality spoofs. Taking a snapshot picture\nis much simpler than developing fingerprints left on a surface by magnetic\npowders and lifting the trace by a tape. What we are interested here is to\nevaluate preliminary at which extent attacks of the kind can be considered a\nreal threat for state-of-art fingerprint liveness detectors and verification\nsystems. To this aim, we collected a novel data set of live and spoof images\nfabricated with snapshot pictures of latent fingerprints. This data set provide\na set of attacks at the most favourable conditions. We refer to this method and\nthe related data set as "ScreenSpoof". Then, we tested with it the performances\nof the best liveness detection algorithms, namely, the three winners of the\nLivDet competition. Reported results point out that the ScreenSpoof method is a\nthreat of the same level, in terms of detection and verification errors, than\nthat of attacks using spoofs fabricated with the full consensus of the victim.\nWe think that this is a notable result, never reported in previous work.\n