Strategy and Feasibility Study for the Construction of High Resolution Images Adversarial Against Convolutional Neural Networks

in ACIIDS 2022: Intelligent Information and Database Systems (2022)

Evolutionary Algorithm-based images, humanly indistinguishable and adversarial against Convolutional Neural Networks: efficiency and filter robustness

in IEEE Access (2021)

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

in Journal of Information and Telecommunication (2020)

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 ... [more ▼]

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. For any category cA of CIFAR-10, one chooses an image A classified by VGG-16 as belonging to cA. From there, two scenarios are addressed. In the first scenario, a target category ct≠cA is fixed a priori. We construct an evolutionary algorithm that evolves A to a modified image that VGG-16 classifies as belonging to ct. In the second scenario, we construct another evolutionary algorithm that evolves A to a modified image that VGG-16 is unable to classify. In both scenarios, the obtained adversarial images remain so close to the original one that a human would likely classify them as still belonging to cA. [less ▲]