@InProceedings{TabacofVall:2017:ExAdIm,
               author = "Tabacof, Pedro and Valle, Eduardo",
          affiliation = "{University of Campinas} and {University of Campinas}",
                title = "Exploring Adversarial Images in Deep Neural Networks",
            booktitle = "Proceedings...",
                 year = "2017",
               editor = "Torchelsen, Rafael Piccin and Nascimento, Erickson Rangel do and 
                         Panozzo, Daniele and Liu, Zicheng and Farias, Myl{\`e}ne and 
                         Viera, Thales and Sacht, Leonardo and Ferreira, Nivan and Comba, 
                         Jo{\~a}o Luiz Dihl and Hirata, Nina and Schiavon Porto, Marcelo 
                         and Vital, Creto and Pagot, Christian Azambuja and Petronetto, 
                         Fabiano and Clua, Esteban and Cardeal, Fl{\'a}vio",
         organization = "Conference on Graphics, Patterns and Images, 30. (SIBGRAPI)",
            publisher = "Sociedade Brasileira de Computa{\c{c}}{\~a}o",
              address = "Porto Alegre",
             keywords = "deep learning, neural networks, adversarial images.",
             abstract = "Adversarial examples have raised questions regarding the 
                         robustness and security of deep neural networks. In this work we 
                         formalize the problem of adversarial images given a pre-trained 
                         classifier, showing that even in the linear case the resulting 
                         optimization problem is nonconvex. We generate adversarial images 
                         using deep classifiers on the ImageNet dataset. We probe the pixel 
                         space of adversarial images using noise of varying intensity and 
                         distribution. We bring novel visualizations that showcase the 
                         phenomenon and its high variability. We show that adversarial 
                         images appear in large regions in the pixel space, and that it is 
                         hard to leave those regions by adding noise to the images, even 
                         with high intensity.",
  conference-location = "Niter{\'o}i, RJ, Brazil",
      conference-year = "17-20 Oct. 2017",
             language = "en",
                  ibi = "8JMKD3MGPAW/3PK8JAB",
                  url = "http://urlib.net/ibi/8JMKD3MGPAW/3PK8JAB",
           targetfile = "sibgrapi (1).pdf",
        urlaccessdate = "2024, May 01"
}