Evolutionary algorithms deceive humans and machines at image classification: An extended proof of concept on two scenarios

The range of applications of Neural Networks encompasses image classification. However, Neural Networks are vulnerable to attacks, and may misclassify adversarial images, leading to potentially disastrous consequences. Pursuing some of our previous work, we provide an extended proof of concept of a black-box, targeted, non-parametric attack using evolutionary algorithms to fool both Neural Networks and humans at the task of image classification. Our feasibility study is performed on VGG-16 trained on CIFAR-10.
Nội dung trích xuất từ tài liệu:
Evolutionary algorithms deceive humans and machines at image classification: An extended proof of concept on two scenarios