abstract

• Foster the mechanical design of artificial vision requires a delicate balance between high-level analytical methods and the discovery through metaheuristics of near-optimal functions working towards complex visual problems. Evolutionary computation and swarm intelligence have developed strategies that automatically design meaningful deep convolutional neural network architectures to create better image classifiers. However, these architectures have not surpassed hand-craft models working with outdated problems with datasets of icon images. Nowadays, recent concerns about deep convolutional neural networks to adversarial attacks in the form of modifications to the input image can manipulate their output to make them untrustworthy. Brain programming is a hyper-heuristic whose aim is to work at a higher level of abstraction to develop automatically artificial visual cortex algorithms for a problem domain like image classification. This work%27s primary goal is to employ brain programming to design an artificial visual cortex to produce accurate and robust image classifiers in two problems. We analyze the final models designed by brain programming with the assumption of fooling the system using two adversarial attacks. In both experiments, brain programming constructed artificial brain models capable of competing with hand-crafted deep convolutional neural networks without any influence in the predictions when an adversarial attack is present. © 2021 ACM.
• Foster the mechanical design of artificial vision requires a delicate balance between high-level analytical methods and the discovery through metaheuristics of near-optimal functions working towards complex visual problems. Evolutionary computation and swarm intelligence have developed strategies that automatically design meaningful deep convolutional neural network architectures to create better image classifiers. However, these architectures have not surpassed hand-craft models working with outdated problems with datasets of icon images. Nowadays, recent concerns about deep convolutional neural networks to adversarial attacks in the form of modifications to the input image can manipulate their output to make them untrustworthy. Brain programming is a hyper-heuristic whose aim is to work at a higher level of abstraction to develop automatically artificial visual cortex algorithms for a problem domain like image classification. This work's primary goal is to employ brain programming to design an artificial visual cortex to produce accurate and robust image classifiers in two problems. We analyze the final models designed by brain programming with the assumption of fooling the system using two adversarial attacks. In both experiments, brain programming constructed artificial brain models capable of competing with hand-crafted deep convolutional neural networks without any influence in the predictions when an adversarial attack is present. © 2021 ACM.

authors

• Olague G.
• Puente Montejano César Augusto
• Soubervielle Montalvo Carlos

publication date

• 2021-01-01

funding provided via

• Consejo Nacional de Ciencia y Tecnología, CONACYT: 469034-560085  Grant

published in

• GECCO 2021 Companion - Proceedings of the 2021 Genetic and Evolutionary Computation Conference Companion  Proceedings

keywords

• adversarial attacks; art media categorization; brain programming; convolutional neural networks; face recognition; secure Brain models; Calculations; Convolution; Convolutional neural networks; Deep neural networks; Heuristic algorithms; Network architecture; Analytical method; Artificial brain; Automated design; Image Classifiers; Level of abstraction; Mechanical design; Meta heuristics; Visual cortexes; Image classification

Digital Object Identifier (DOI)

• 10.1145/3449726.3463179

PubMed ID

start page

• 1385

end page

• 1393

volume

issue