Measuring and mitigating targeted biometric impersonation

Abstract

This study is concerned with the reliability of biometric verification systems when used in forensic applications. In particular, when such systems are subjected to targeted impersonation attacks. The authors expand on the existing work in targeted impersonation, focusing on how best to measure the reliability of verification systems in forensic contexts. It identifies two scenarios in which targeted impersonation effects may occur: (i) the forensic investigation of criminal activity involving identity theft; and (ii) implicit targeting as a result of the forensic investigation process. Also, the first partial countermeasure to such attacks is presented. The countermeasure uses client-specific Z-score normalisation to provide a more consistent false acceptance rate across all enrolled subjects. This reduces the effectiveness of targeted impersonation without impairing the systems accuracy under random zero-effort attacks.

Emerging Biometrics: Deep Inference and Other Computational Intelligence

“…This MRF model does not use high order cliques but still reaches globally coherent solutions. In [18], the mitigation of targeted biometric impersonation has been proposed. Targeted impersonation is defined as a method of spoofing the biometric traits.…”

Cognitive checkpoint: Emerging technologies for biometric-enabled watchlist screening

“…This suggests that interview supporting technologies should be integrated in these machines. From this perspective, our analysis delivers the following technology landscape: 1) Dynamical probabilistic models [64], [89]; they better reflect layered security properties; 2) Deep inference in traveler risk assessment [49]; 3) Predictive analytic and modeling including deep learning in traffic flow prediction [57]; 4) Traveler surveillance in physical world [10], [33], and virtual/digital world [9]; 5) Managing distributed resources [25]; 6) Attack countermeasures [5], [12], [14], [27]; 7) Technology gaps identification [36], [49], [80], including attack mitigation [63].…”

Face recognition under spoofing attacks: countermeasures and research directions

“…An adequate spoofing detection method should meet a certain number of practical requirements [9, 29]. For instance, (i) the method should be non‐invasive, i.e.…”