18 datasets found

The dataset used in the paper is COCO and D2-City, which are commonly used detection datasets.

Face recognition is a popular form of biometric authentication and due to its widespread use, attacks have become more common as well. Recent studies show that Face Recognition...

This paper presents a well-known music identification method and implements it as a neural net.

The dataset used in the paper is not explicitly described, but it is mentioned that the authors used the Google Cloud Vision platform to test their attack.

The dataset used for testing the effectiveness of Landmark Breaker in disrupting facial landmark extraction and obstructing DeepFake generation.

The Imagenette dataset used in the paper for class density and dataset quality in high-dimensional, unstructured data.

Breast cancer dataset where mammograms have been labeled independently by three doctors. Ground-truth has been obtained through a biopsy, not available to the algorithm nor the...

The MNIST dataset is a large dataset of handwritten digits, and the CIFAR-10 dataset is a dataset of images from 10 different classes.

The dataset used in the paper is the Alibaba Tianchi competition: Alibaba-Tsinghua Adversarial Challenge on Object Detection.

Trajectory prediction plays an essential role in autonomous vehicles. While numerous strategies have been developed to enhance the robustness of trajectory prediction models,...

A novel framework for a geometric adversarial attack on 3D mesh autoencoders.

The dataset used in the paper is not explicitly described, but it is mentioned that the authors used the NeurIPS'17 adversarial competition dataset, compatible with ImageNet,...

This work investigates the robustness of SAM to corruptions and adversarial attacks.

Video object segmentation has been applied to various computer vision tasks, such as video editing, autonomous driving, and human-robot interaction.

The dataset used in the paper is CIFAR-10 and NIPS-W, which are benchmark datasets for image classification and adversarial attacks.

A binary imbalanced classification dataset with 32 × 32 color images of 10 classes of natural objects.

This paper investigates the impact of different standard environmental sound representations (spectrograms) on the recognition performance and adversarial attack robustness of a...

The MNIST and CIFAR10 datasets are used to evaluate the Cycle-Consistent Adversarial GAN (CycleAdvGAN) for image classification.