adversarial-attack
adversarial_loss_lr_1e-5_attack_meta-llama_Llama-2-7b-chat-hf_masked_4_3e-5_1kadversarial_loss_lr_1e-5_attack_meta-llama_Llama-2-7b-chat-hf_4_3e-5_1kadversarial_loss_lr_1e-5_attack_meta-llama_Llama-2-7b-chat-hf_4_8e-5_10kadversarial_loss_lr_1e-5_attack_meta-llama_Llama-2-7b-chat-hf_masked_4_6e-5_1kadversarial_loss_lr_1e-5_attack_meta-llama_Llama-2-7b-chat-hf_4_num_layers_6_8e-5_1kadversarial_loss_lr_1e-5_attack_meta-llama_Llama-2-7b-chat-hf_4_num_layers_6_3e-5_1kadversarial_loss_lr_1e-5_attack_meta-llama_Llama-2-7b-chat-hf_4_num_layers_6_6e-5_1kadversarial_loss_lr_1e-5_attack_meta-llama_Llama-2-7b-chat-hf_4_6e-5_1k
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_attacksage-adversarial-attack
Age Adversarial Attack Dataset
Paper: Can a Teenager Fool an AI? Evaluating Low-Cost Cosmetic Attacks on Age Estimation SystemsAuthors: Simiao Ren (Reality Inc. / Duke University)
Overview
This dataset contains 5,809 AI-generated adversarial images derived from a curated set of 329 face images (ages 10–21) drawn from six standard age estimation benchmarks. Each image is a VLM-simulated cosmetic attack designed to make age estimation models misclassify a subject… See the full description on the dataset page: https://huggingface.co/datasets/Scam-AI/age-adversarial-attack.