A survey of robustness and safety of 2d and 3d deep learning models against adversarial attacks

Y Li, B Xie, S Guo, Y Yang, B Xiao - ACM Computing Surveys, 2024 - dl.acm.org
Benefiting from the rapid development of deep learning, 2D and 3D computer vision
applications are deployed in many safe-critical systems, such as autopilot and identity …

Benchmarking image classifiers for physical out-of-distribution examples detection

O Ojaswee, A Agarwal, N Ratha - Proceedings of the IEEE …, 2023 - openaccess.thecvf.com
The rising popularity of deep neural networks (DNNs) in computer vision has raised
concerns about their robustness in the real world. Recent works in this field have well …

Recognition-oriented image compressive sensing with deep learning

S Zhou, X Deng, C Li, Y Liu… - IEEE Transactions on …, 2022 - ieeexplore.ieee.org
A number of image compressive sensing (CS) algorithms were proposed in the past two
decades, aiming at yielding recovered images with the best possible visual effect. However …

Image transformation-based defense against adversarial perturbation on deep learning models

A Agarwal, R Singh, M Vatsa… - IEEE Transactions on …, 2020 - ieeexplore.ieee.org
Deep learning algorithms provide state-of-the-art results on a multitude of applications.
However, it is also well established that they are highly vulnerable to adversarial …

Crafting adversarial perturbations via transformed image component swapping

A Agarwal, N Ratha, M Vatsa… - IEEE Transactions on …, 2022 - ieeexplore.ieee.org
Adversarial attacks have been demonstrated to fool the deep classification networks. There
are two key characteristics of these attacks: firstly, these perturbations are mostly additive …

Robustness against gradient based attacks through cost effective network fine-tuning

A Agarwal, N Ratha, R Singh… - Proceedings of the IEEE …, 2023 - openaccess.thecvf.com
Adversarial perturbations aim to modify the image pixels in an imperceptible manner such
that the CNN classifier misclassifies an image, whereas humans can predict the original …

Damad: Database, attack, and model agnostic adversarial perturbation detector

A Agarwal, G Goswami, M Vatsa… - … on Neural Networks …, 2021 - ieeexplore.ieee.org
Adversarial perturbations have demonstrated the vulnerabilities of deep learning algorithms
to adversarial attacks. Existing adversary detection algorithms attempt to detect the …

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 …

Privacy-preserving link scheduling for wireless networks

M Abbasalizadeh, J Chan, P Rayavaram, Y Chen… - IEEE …, 2024 - ieeexplore.ieee.org
Wireless communication is now a cornerstone of modern society, propelled by the
widespread adoption of IoT devices and sophisticated wireless technologies. As wireless …

Offloading deep learning empowered image segmentation from uav to edge server

HE Ilhan, S Ozer, GK Kurt… - 2021 44th International …, 2021 - ieeexplore.ieee.org
Image and video analysis in unmanned aerial vehicle (UAV) systems have been a recent
interest in many applications since the images taken by UAV systems can provide useful …