%0 Journal Article
%T Adversarial Framing for Image and Video Classification
%A Zając, Michał
%A Żołna, Konrad
%A Rostamzadeh, Negar
%A Pinheiro, Pedro O.
%J Schedae Informaticae
%V 2018
%R 10.4467/20838476SI.18.012.10417
%N Volume 27
%P 155-164
%K adversarial samples, convolutional neural networks, classification
%@ 1732-3916
%D 2018
%U https://ejournals.eu/en/journal/schedae-informaticae/article/adversarial-framing-for-image-and-video-classification
%X 
	Neural networks are prone to adversarial attacks. In general, such attacks deteriorate the quality of the input by either slightly modifying most of its pixels, or by occluding it with a patch. In this paper, we propose a method that keeps the image unchanged and only adds an adversarial framing on the border of the image. We show empirically that our method is able to successfully attack state-of-the-art methods on both image and video classification problems. Notably, the proposed method results in a universal attack which is very fast at test time.