Cancelable Fingerprint Template Construction Using Vector Permutation and Shift-Ordering

Biometric Template Attacks and Recent Protection Mechanisms: A Survey

“…Baghel et al [78] utilized a non-invertible transformation to specifically combat brute-force and false-accept attacks, while Li et al [76] improved on the concept of IoM hashing to derive an indexing min-max hashing technique to mitigate these attacks. Recently, Abdullahi et al [82] developed a vector permutation and shift-ordering approach to mitigate these attacks.…”

“…To mitigate other attacks such as similarity-based, hill-climbing, preimage, correlation, crossmatch, masquerade, and substitution in fingerprint and face biometric features, Yang et al [100] and Agarwal and Bansal [79] are able to use a linear convolution and an alignment-free non-invertible transformation function, respectively, to mitigate cross-matching attacks. Similarity correlation, pre-image, dictionary, and masquerade attacks were also mitigated in the works of Abdullahi et al [82] and Sardar et al [85]. Apart from inversion and masquerade attacks, Bedari et al [77] also use the Dyno key model to overcome attacks related to revoked templates.…”

“…11(c) and 11(d) depicts the performance of techniques against inversion and ARM on FVC2004 datasets, respectively. It can be seen that the most recently published techniques, including AFN-TF [79], VP-SO [82], and IMMH [76], designed to mitigate inversion attacks, achieve better recognition accuracy (performance preservation) in both datasets than the other techniques, while PR-NNLS [73] and NT [78] have the least performance, especially on DB3 of FVC2002 and DB2 of FVC2004, respectively. However, for techniques designed to mitigate ARM attacks, M-FF [121], FC-FMT [127], and DF-CFM [125] achieve better performance than other techniques in the same category on both FVC datasets.…”

“…Furthermore, in the case of a lost key, a feature-guided index-generating method is designed to guarantee the security of the selected help vector. Other recent techniques used to counter the inversion of fingerprint templates include the works of Baghel et al [78], Agarwal and Bansal [79], Guo et al [80], Trivedi et al [81], and Abdullahi et al [82].…”

“…The EER comparison of 10 protection mechanisms is made in this category. This includes the techniques of Wang et al [74], abbreviated as PHD; Jin et al [75] as IoM; Kho et al [73] as PR-NNLS; Trivedi et al [99] as DT-MP; Badari et al [77] as DKM; Baghel et al [78] as NT; Li et al [76] as IMMH; Yang et al [100] as LC; Agarwal and Bansal [79] as AFN-TF; and Abdullahi et al [82] as VP-SO; on inversion attacks. The techniques of Wang et al [123] as ZMP, Ariona et al [125] as DF-CFM, Abdullahi et al [127] as FC-FMT, Tran and Hu [121] as M-FF, Shahzad et al [122] as WS-PDWT, and Yang et al [128] as FARP on ARM attacks.…”