Robust Image Classification in the Presence of Out-of-Distribution and Adversarial Samples Using Attractors in Neural Networks

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Alipour, Nasrin, SeyyedSalehi, Seyyed Ali
Natura: Preprint
Pubblicazione: 2024
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866909225169453056
author Alipour, Nasrin
SeyyedSalehi, Seyyed Ali
author_facet Alipour, Nasrin
SeyyedSalehi, Seyyed Ali
contents The proper handling of out-of-distribution (OOD) samples in deep classifiers is a critical concern for ensuring the suitability of deep neural networks in safety-critical systems. Existing approaches developed for robust OOD detection in the presence of adversarial attacks lose their performance by increasing the perturbation levels. This study proposes a method for robust classification in the presence of OOD samples and adversarial attacks with high perturbation levels. The proposed approach utilizes a fully connected neural network that is trained to use training samples as its attractors, enhancing its robustness. This network has the ability to classify inputs and identify OOD samples as well. To evaluate this method, the network is trained on the MNIST dataset, and its performance is tested on adversarial examples. The results indicate that the network maintains its performance even when classifying adversarial examples, achieving 87.13% accuracy when dealing with highly perturbed MNIST test data. Furthermore, by using fashion-MNIST and CIFAR-10-bw as OOD samples, the network can distinguish these samples from MNIST samples with an accuracy of 98.84% and 99.28%, respectively. In the presence of severe adversarial attacks, these measures decrease slightly to 98.48% and 98.88%, indicating the robustness of the proposed method.
format Preprint
id arxiv_https___arxiv_org_abs_2406_10579
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Robust Image Classification in the Presence of Out-of-Distribution and Adversarial Samples Using Attractors in Neural Networks
Alipour, Nasrin
SeyyedSalehi, Seyyed Ali
Computer Vision and Pattern Recognition
Machine Learning
Image and Video Processing
The proper handling of out-of-distribution (OOD) samples in deep classifiers is a critical concern for ensuring the suitability of deep neural networks in safety-critical systems. Existing approaches developed for robust OOD detection in the presence of adversarial attacks lose their performance by increasing the perturbation levels. This study proposes a method for robust classification in the presence of OOD samples and adversarial attacks with high perturbation levels. The proposed approach utilizes a fully connected neural network that is trained to use training samples as its attractors, enhancing its robustness. This network has the ability to classify inputs and identify OOD samples as well. To evaluate this method, the network is trained on the MNIST dataset, and its performance is tested on adversarial examples. The results indicate that the network maintains its performance even when classifying adversarial examples, achieving 87.13% accuracy when dealing with highly perturbed MNIST test data. Furthermore, by using fashion-MNIST and CIFAR-10-bw as OOD samples, the network can distinguish these samples from MNIST samples with an accuracy of 98.84% and 99.28%, respectively. In the presence of severe adversarial attacks, these measures decrease slightly to 98.48% and 98.88%, indicating the robustness of the proposed method.
title Robust Image Classification in the Presence of Out-of-Distribution and Adversarial Samples Using Attractors in Neural Networks
topic Computer Vision and Pattern Recognition
Machine Learning
Image and Video Processing
url https://arxiv.org/abs/2406.10579