Zobrazeno 1 - 3
of 3
pro vyhledávání: '"Saad, Rodrigo T."'
Convolutional neural networks (CNNs) are fragile to small perturbations in the input images. These networks are thus prone to malicious attacks that perturb the inputs to force a misclassification. Such slightly manipulated images aimed at deceiving
Externí odkaz:
http://arxiv.org/abs/2102.04615
Publikováno v:
In Journal of Visual Communication and Image Representation May 2023 93
Publikováno v:
Automated Technology for Verification & Analysis (9783642333859); 2012, p284-299, 16p