datasets
Training and evaluation data, with the modality, task and licence stated up front. Listed live from the Hugging Face Hub.
efficientnet-v2-l-adv-dataset
Perturb Adversarial Images
Verified adversarial examples for efficientnet_v2_l (torchvision/EfficientNet_V2_L_Weights.IMAGENET1K_V1), produced by the
Perturb network. Each row is one clean image together with all of its
verified adversarial versions: images that are imperceptibly different from the original
(L∞ ≤ 0.03 in [0,1] pixel scale) yet change the model's top-1 prediction.
This dataset grows continuously. New rows are appended as the network produces them and uploaded in… See the full description on the dataset page: https://huggingface.co/datasets/perturb-ai/efficientnet-v2-l-adv-dataset.perturbed_faces
Perturbed Faces
This dataset contains 1000 images from CelebA dataset. For each of the thousand images dataset also has LowKey perturbed version and Fawkes perturbed version.
LowKey and Fawkes perturbed images have _attacked & _cloaked at the end of the filename respectively.
File Name
Version
000001.jpg
Original
000001_cloaked.png
Fawkes perturbed version
000001_attacked.png
LowKey perturbed version
The Fawkes perturbed images are created using CLI provided in… See the full description on the dataset page: https://huggingface.co/datasets/aadityaubhat/perturbed_faces.