Anzeige
Erschienen in:
2020 | OriginalPaper | Buchkapitel
Computational Analysis of Robustness in Neural Network Classifiers
verfasst von : Iveta Bečková, Štefan Pócoš, Igor Farkaš
Erschienen in: Artificial Neural Networks and Machine Learning – ICANN 2020
Aktivieren Sie unsere intelligente Suche, um passende Fachinhalte oder Patente zu finden.
Wählen Sie Textabschnitte aus um mit Künstlicher Intelligenz passenden Patente zu finden. powered by
Markieren Sie Textabschnitte, um KI-gestützt weitere passende Inhalte zu finden. powered by
Abstract
Neural networks, especially deep architectures, have proven excellent tools in solving various tasks, including classification. However, they are susceptible to adversarial inputs, which are similar to original ones, but yield incorrect classifications, often with high confidence. This reveals the lack of robustness in these models. In this paper, we try to shed light on this problem by analyzing the behavior of two types of trained neural networks: fully connected and convolutional, using MNIST, Fashion MNIST, SVHN and CIFAR10 datasets. All networks use a logistic activation function whose steepness we manipulate to study its effect on network robustness. We also generated adversarial examples with FGSM method and by perturbing those pixels that fool the network most effectively. Our experiments reveal a trade-off between accuracy and robustness of the networks, where models with a logistic function approaching a threshold function (very steep slope) appear to be more robust against adversarial inputs.