Masquerade attack on transform-based binary-template protection based on perceptron learning

作者：

Highlights：

• We propose masquerade attacks to violate the security of transform-based binary template protection schemes.

• We identify two different attacking scenarios and develop a perceptron-learning-based attack for each.

• Our attack algorithms allow offline iterative processing in the generation of synthetic biometric image.

• We obtain very encouraging empirical results for our attack algorithms on two benchmark face datasets.

摘要

Highlights•We propose masquerade attacks to violate the security of transform-based binary template protection schemes.•We identify two different attacking scenarios and develop a perceptron-learning-based attack for each.•Our attack algorithms allow offline iterative processing in the generation of synthetic biometric image.•We obtain very encouraging empirical results for our attack algorithms on two benchmark face datasets.

论文关键词：Masquerade attack,Binary,Template protection,Perceptron learning

论文评审过程：Received 29 August 2013, Revised 24 February 2014, Accepted 6 March 2014, Available online 15 March 2014.

论文官网地址：https://doi.org/10.1016/j.patcog.2014.03.003