000			01428nam a2200169 a 4500
005			20260901030334.0
008			250101s2019 xx o 000 0 eng d
100	1		_aKazuya Kakizaki
245	1	0	_aAdversarial Image Translation: Unrestricted Adversarial Examples in Face Recognition Systems
264		1	_barXiv _c2019
336			_atext
338			_aonline resource
520			_aThanks to recent advances in deep neural networks (DNNs), face recognition systems have become highly accurate in classifying a large number of face images. However, recent studies have found that DNNs could be vulnerable to adversarial examples, raising concerns about the robustness of such systems. Adversarial examples that are not restricted to small perturbations could be more serious since conventional certified defenses might be ineffective against them. To shed light on the vulnerability to such adversarial examples, we propose a flexible and efficient method for generating unrestricted adversarial examples using image translation techniques. Our method enables us to translate a source image into any desired facial appearance with large perturbations to deceive target face recognition systems. Our experimental results indicate that our method achieved about $90$ and $80\%$ attack
506	0		_aOpen access — freely available to read.
856	4	0	_uhttps://arxiv.org/pdf/1905.03421v3 _yRead the full paper (PDF)
942			_cERES
999			_c651 _d651