Adversarial attacks on deep learning networks in image classification based on Smell Bees Optimization Algorithm

• Published in: Future generation computer systems 2023-03, Vol.140, p.185-195
• Main Author: Mohamed Ben Ali, Yamina
• Format: Article
• Language: English
• Subjects: Adversarial generation example; Black box attack; Deep learning neural networks; Smell bees optimization algorithm; Steganography
• ISSN: 0167-739X; 1872-7115
• DOI: 10.1016/j.future.2022.10.022

Adversarial machine learning is an active trend in artificial intelligence that attempts to fool deep learning models by causing malfunctions during the prediction of decisions. In this work, we are interested in image classification, and propose a black box for adversarial examples generation which is driven by an optimization algorithm. The main ideas of the used approach are firstly inspired from the steganography principles in which hiding information in image pixels with minimal payload capacity to reduce the distortion between the real image and the adversarial image constitutes a constraint to be respected. In fact, this distance must be sufficient to lead to deceive an already trained classifier. Secondly, the selection of relevant pixels for embedding information bits is mainly done by the optimization algorithm Smell Bees Optimization (SBO). Some investigations are done on Convolutional neural network, Softmax classifier and Residual network, providing good results on both MINST and CIFAR datasets. [Display omitted]