A Deep Genetic Programming Based Methodology for Art Media Classification Robust to Adversarial Perturbations

Created by W.Langdon from gp-bibliography.bib Revision:1.7630

@InProceedings{Olague:2020:ISVC,

• author = "Gustavo Olague and Gerardo Ibarra-Vazquez and Mariana Chan-Ley and Cesar Puente and Carlos Soubervielle-Montalvo and Axel Martinez",
• title = "A Deep Genetic Programming Based Methodology for Art Media Classification Robust to Adversarial Perturbations",
• booktitle = "Advances in Visual Computing. ISVC 2020, Part I",
• year = "2020",
• editor = "George Bebis and Zhaozheng Yin and Edward Kim and Jan Bender and Kartic Subr and Bum Chul Kwon and Jian Zhao and Denis Kalkofen and George Baciu",
• volume = "12509",
• series = "LNCS",
• pages = "68--79",
• address = "San Diego, CA, USA",
• month = oct # " 5-7",
• publisher = "Springer",
• keywords = "genetic algorithms, genetic programming, Brain Programming, Deep learning, Symbolic learning, Art media classification, Adversarial attacks",
• isbn13 = "978-3-030-64555-7",
• URL = "http://www.human-competitive.org/sites/default/files/olague-humies2021-final_0.txt",
• URL = "http://www.human-competitive.org/sites/default/files/olague-isvc2020.pdf",
• DOI = "doi:10.1007/978-3-030-64556-4_6",
• size = "12 pages",
• abstract = "Art Media Classification problem is a current research area that has attracted attention due to the complex extraction and analysis of features of high-value art pieces. The perception of the attributes can not be subjective, as humans sometimes follow a biased interpretation of artworks while ensuring automated observation trustworthiness. Machine Learning has out performed many areas through its learning process of artificial feature extraction from images instead of designing handcrafted feature detectors. However, a major concern related to its reliability has brought attention because, with small perturbations made intentionally in the input image (adversarial attack), its prediction can be completely changed. In this manner, we foresee two ways of approaching the situation: (1) solve the problem of adversarial attacks in current neural networks methodologies, or (2) propose a different approach that can challenge deep learning without the effects of adversarial attacks. The first one has not been solved yet, and adversarial attacks have become even more complex to defend. Therefore, this work presents a Deep Genetic Programming method, called Brain Programming, that competes with deep learning and studies the transferability of adversarial attacks using two artworks databases made by art experts. The results show that the Brain Programming method preserves its performance in comparison with AlexNet, making it robust to these perturbations and competing to the performance of Deep Learning.",
• notes = "Entered 2021 HUMIES",

}

Genetic Programming entries for Gustavo Olague Gerardo Ibarra-Vazquez Mariana Chan-Ley Cesar Puente Carlos Soubervielle-Montalvo Axel Martinez

Citations