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)

Empirical Perturbation Analysis of Two Adversarial Attacks: Black Box versus White Box

in Applied Sciences (2022), 12(14), 7339

Robustness of Adversarial Images against Filters

in Optimization and Learning (2021), 1443

Universities and Civilizations

Book published by ISTE and Wiley (2021)

Since the publication of the first Shanghai ranking in 2003, the international rankings of universities have become evermore important. This book examines the evolution of higher education systems and the ... [more ▼]

Since the publication of the first Shanghai ranking in 2003, the international rankings of universities have become evermore important. This book examines the evolution of higher education systems and the role of universities in contemporary societies, which are marked by increased competition and tensions. Investigating whether the dynamism of universities is an accurate indicator of the intellectual life of their civilizations, Universities and Civilizations systematically analyzes the evolution of universities in several main rankings, from their creation until now. [less ▲]

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 ▲]

Reducing overfitting and improving generalization in training convolutional neural network under limited sample sizes in image recognition

in 5th International Conference on Information Technology, Bangsaen 21-22 October 2020 (2020)

How Evolutionary Algorithms and Information Hiding deceive machines and humans for image recognition: A research program

in Theeramunkong, Thanaruk; Bouvry, Pascal; Srichaikul, Piyawut (Eds.) Proceedings of the OLA'2019 International Conference on Optimization and Learning (Bangkok, Thailand, Jan 29-31, 2019) (2019)

Deep Neural Networks are used for a wide range of critical applications, notably for image recognition. The ability to deceive their recognition abilities is an active research domain, since successful ... [more ▼]

Deep Neural Networks are used for a wide range of critical applications, notably for image recognition. The ability to deceive their recognition abilities is an active research domain, since successful deceptions may have disastrous consequences. Still, humans sometimes detect mistakes made by machines when they classify images. One can conceive a system able to solicit humans in case of doubts, namely when humans and machines may disagree. Using Information Hiding techniques, we describe a strategy to construct evolutionary algorithms able to fool both neural networks and humans for image recognition. Although this research is still exploratory, we already describe a concrete fitness function for a specific scenario. Additional scenarii and further research directions are provided. [less ▲]

The University of Luxembourg: A National Excellence Initiative

in Altbach, Phil; Reisberg, Liz; Salmi, Jamil (Eds.) et al Accelerated Universities: A ideas and Money Combine to Build Academic Excellence (2018)

Evolutionary Algorithms for Convolutional Neural Network Visualisation

in Meneses, Esteban; Castro, Harold; Barrios Hernández, Carlos Jaime (Eds.) et al High Performance Computing -- 5th Latin American Conference, CARLA 2018, Piedecuesta, Colombia (2018)

Deep Learning is based on deep neural networks trained over huge sets of examples. It enabled computers to compete with ---~or even outperform~--- humans at many tasks, from playing Go to driving ... [more ▼]

Deep Learning is based on deep neural networks trained over huge sets of examples. It enabled computers to compete with ---~or even outperform~--- humans at many tasks, from playing Go to driving vehicules. Still, it remains hard to understand how these networks actually operate. While an observer sees any individual local behaviour, he gets little insight about their global decision-making process. However, there is a class of neural networks widely used for image processing, convolutional networks, where each layer contains features working in parallel. By their structure, these features keep some spatial information across a network's layers. Visualisation of this spatial information at different locations in a network, notably on input data that maximise the activation of a given feature, can give insights on the way the model works. This paper investigates the use of Evolutionary Algorithms to evolve such input images that maximise feature activation. Compared with some pre-existing approaches, ours seems currently computationally heavier but with a wider applicability. [less ▲]

Security and Intelligent Information Systems

Book published by Springer (2012)