01382nam a2200145 a 450000500170000000800400001710000200005724500970007726400160017433600090019033800200019952009050021950600460112485600660117020260901030334.0250101s2019    xx     o     000 0 eng d1 aKazuya Kakizaki10aAdversarial Image Translation: Unrestricted Adversarial Examples in Face Recognition Systems 1barXivc2019  atext  aonline resource  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 0 aOpen access — freely available to read.40uhttps://arxiv.org/pdf/1905.03421v3yRead the full paper (PDF)