Just Noticeable Difference for Machines to Generate Adversarial Images

Autor:	Akan, Adil Kaan, Genc, Mehmet Ali, Vural, Fatos T. Yarman
Rok vydání:	2020
Předmět:	Electrical Engineering and Systems Science - Image and Video Processing Computer Science - Computer Vision and Pattern Recognition
Druh dokumentu:	Working Paper
Popis:	One way of designing a robust machine learning algorithm is to generate authentic adversarial images which can trick the algorithms as much as possible. In this study, we propose a new method to generate adversarial images which are very similar to true images, yet, these images are discriminated from the original ones and are assigned into another category by the model. The proposed method is based on a popular concept of experimental psychology, called, Just Noticeable Difference. We define Just Noticeable Difference for a machine learning model and generate a least perceptible difference for adversarial images which can trick a model. The suggested model iteratively distorts a true image by gradient descent method until the machine learning algorithm outputs a false label. Deep Neural Networks are trained for object detection and classification tasks. The cost function includes regularization terms to generate just noticeably different adversarial images which can be detected by the model. The adversarial images generated in this study looks more natural compared to the output of state of the art adversarial image generators. Comment: 5 pages, 4 figures, submitted to ICIP2020
Databáze:	arXiv
Externí odkaz:	http://arxiv.org/abs/2001.11064 Zobrazit plný text záznamu View this record from Arxiv