Morphing-Attacks Against Binary Fingervein Templates

For the first time, the feasibility of creating morphed templates for attacking vascular biometrics is investigated, in particular finger vein recognition schemes generating binary vascular patterns are addressed. A conducted vulnerability analysis reveals that (i) the extent of vulnerability, (ii) the type of most vulnerable recognition scheme, and (iii) the preferred way to construct the morphed template for a given target template depends on the employed sensor. It turns out that targeted template doppelgaenger selection is important for an attack success. The identified threat level in terms of IAPMR is often found to be \(> 0.8\) for several sensor/template generation scheme/morphing technique combinations. Thus, the risk as imposed by such attacks can be said to be considerable.