A survey of robustness and safety of 2d and 3d deep learning models against adversarial attacks
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 …
applications are deployed in many safe-critical systems, such as autopilot and identity …
Benchmarking image classifiers for physical out-of-distribution examples detection
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 …
concerns about their robustness in the real world. Recent works in this field have well …
Recognition-oriented image compressive sensing with deep learning
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 …
decades, aiming at yielding recovered images with the best possible visual effect. However …
Image transformation-based defense against adversarial perturbation on deep learning models
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 …
However, it is also well established that they are highly vulnerable to adversarial …
Crafting adversarial perturbations via transformed image component swapping
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 …
are two key characteristics of these attacks: firstly, these perturbations are mostly additive …
Robustness against gradient based attacks through cost effective network fine-tuning
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 …
that the CNN classifier misclassifies an image, whereas humans can predict the original …
Damad: Database, attack, and model agnostic adversarial perturbation detector
Adversarial perturbations have demonstrated the vulnerabilities of deep learning algorithms
to adversarial attacks. Existing adversary detection algorithms attempt to detect the …
to adversarial attacks. Existing adversary detection algorithms attempt to detect the …
Benchmarking Robustness Beyond Norm Adversaries
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 …
examples ranging from adversarial perturbations to common noises to natural adversaries …
Privacy-preserving link scheduling for wireless networks
Wireless communication is now a cornerstone of modern society, propelled by the
widespread adoption of IoT devices and sophisticated wireless technologies. As wireless …
widespread adoption of IoT devices and sophisticated wireless technologies. As wireless …
Offloading deep learning empowered image segmentation from uav to edge server
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 …
interest in many applications since the images taken by UAV systems can provide useful …