AESOP: Adjustable Exhaustive Search for One-Pixel Attacks in Deep Neural Networks
Sign Up to like & getrecommendations! Published in 2023 at "Applied Sciences"
DOI: 10.3390/app13085092
Abstract: Deep neural networks have achieved remarkable performance in various fields such as image recognition and natural language processing. However, recent research has revealed that even a small imperceptible perturbation can confound well-trained neural network models… read more here.
Keywords: neural networks; one pixel; deep neural; pixel attacks ... See more keywords