TY - JOUR
T1 - Adversarial photo frame
T2 - 2019 Working Notes of the MediaEval Workshop, MediaEval 2019
AU - Liu, Zhuoran
AU - Zhao, Zhengyu
N1 - Publisher Copyright:
© 2019 for this paper by its authors. Use permitted under Creative Commons License Attribution 4.0 International (CC BY 4.0).
PY - 2019
Y1 - 2019
N2 - Personal privacy protection has become more and more crucial in the era of big multimedia data and artificial intelligence. This paper presents our submission to pixel privacy task, where we propose to fool the deep visual classification model that is for recognition of sensitive scenes by adding adversarial frame to the image. Experimental results indicate that our method can achieve strong adversarial effects while maintaining the visual appeal and social function of the transformed images.
AB - Personal privacy protection has become more and more crucial in the era of big multimedia data and artificial intelligence. This paper presents our submission to pixel privacy task, where we propose to fool the deep visual classification model that is for recognition of sensitive scenes by adding adversarial frame to the image. Experimental results indicate that our method can achieve strong adversarial effects while maintaining the visual appeal and social function of the transformed images.
UR - https://www.scopus.com/pages/publications/85091588068
M3 - 会议文章
AN - SCOPUS:85091588068
SN - 1613-0073
VL - 2670
JO - CEUR Workshop Proceedings
JF - CEUR Workshop Proceedings
Y2 - 27 October 2019 through 30 October 2019
ER -