datasets
Training and evaluation data, with the modality, task and licence stated up front. Listed live from the Hugging Face Hub.
M-Attack-V2-Adversarial-Samples
M-Attack-V2 Adversarial Samples
Adversarial image samples generated by M-Attack-V2, from the paper:
Pushing the Frontier of Black-Box LVLM Attacks via Fine-Grained Detail Targeting
arXiv:2602.17645 | Project Page | Code
Dataset Structure
├── epsilon_8/ # 100 adversarial images (ε = 8/255)
│ ├── 0.png
│ ├── 1.png
│ ├── ...
│ └── metadata.csv
└── epsilon_16/ # 100 adversarial images (ε = 16/255)
├── 0.png
├── 1.png
├── ...
└──… See the full description on the dataset page: https://huggingface.co/datasets/MBZUAI-LLM/M-Attack-V2-Adversarial-Samples.CLIP-adversarial-typographic-attack_text-image
CLIP-adversarial-typographic-attack_text-image
A typographic attack dataset for CLIP. For adversarial training & model research / XAI (research) use.
First 47 are random and self-made images, rest are from dataset: SPRIGHT-T2I/spright_coco. Of which:
Images are selected for pre-trained OpenAI/CLIP ViT-L/14 features; for highly salient 'text related' concepts via Sparse Autoencoder (SAE).
Labels via CLIP ViT-L/14 gradient ascent -> optimize text embeddings for cosine… See the full description on the dataset page: https://huggingface.co/datasets/zer0int/CLIP-adversarial-typographic-attack_text-image.repro-consistent-adversarial-attacks-traces
Agent traces
Agent sessions published from a Trackio Logbook.
cat-attack-adversarial-triggersdataset_without_adversarial_attacksAdversarial_Attacks_Alignment_Dataset
Adversarial Attacks Alignment Dataset
This dataset contains prompts and responses from various models, including accepted and rejected responses based on specific criteria. The dataset is designed to help in the study and development of adversarial attacks and alignment in reinforcement learning from human feedback (RLHF).
Dataset Details
Prompts: Various prompts used to elicit responses from models.
Accepted Responses: Responses that were accepted based on specific… See the full description on the dataset page: https://huggingface.co/datasets/yaswanth-iitkgp/Adversarial_Attacks_Alignment_Dataset.dataset_without_adversarial_attacks_with_predictions