Exploring robustness connection between artificial and natural adversarial examples

A Agarwal, N Ratha, M Vatsa… - Proceedings of the IEEE …, 2022 - openaccess.thecvf.com
Although recent deep neural network algorithm has shown tremendous success in several
computer vision tasks, their vulnerability against minute adversarial perturbations has raised …

Benchmarking Robustness Beyond Norm Adversaries

A Agarwal, N Ratha, M Vatsa, R Singh - European Conference on …, 2022 - Springer
Recently, a significant boom has been noticed in the generation of a variety of malicious
examples ranging from adversarial perturbations to common noises to natural adversaries …

Intelligent and adaptive mixup technique for adversarial robustness

A Agarwal, M Vatsa, R Singh… - 2021 IEEE International …, 2021 - ieeexplore.ieee.org
Deep neural networks are generally trained using large amounts of data to achieve state-of-
the-art accuracy in many possible computer vision and image analysis applications ranging …

3 Deep Learning in Computer Vision

A Agarwal, N Ratha - … of Artificial Intelligence, Big Data and …, 2022 - books.google.com
Deep learning-based algorithms are classified as automatic feature learning and
classification algorithms. In order to effectively learn these features, these algorithms …

Imperceptible adversarial attack with entropy feature and segmentation-based constraint

R Li, Q Lin, Y Fu, W Xie, L Shen - Proceedings of the 2021 10th …, 2021 - dl.acm.org
Methods of adversarial attack and defense have attracting increasing attention in the fields
of security and protection related applications. However, current algorithms carry out …

[引用][C] 针对未知攻击的泛化性对抗防御技术综述

周大为, 徐一搏, 王楠楠, 刘德成, 彭春蕾, 高新波 - 中国图象图形学报