DAT - Distributional Adversarial Training

arXiv GitHub

DAT utilizes continuous adversarial training on diffusion-based adversarial examples to close the gap between empirical and population-robust risk. We fine-tune meta-llama/Meta-Llama-3-8B-Instruct.

For further information, consult our paper or repository

Citation

@misc{,
      title={}, 
      author={},
      year={2026},
      eprint={},
      archivePrefix={arXiv},
      primaryClass={cs.LG}
}
Downloads last month
33
Safetensors
Model size
8B params
Tensor type
BF16
·
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for ASSELab/DAT-Llama-3-8B-Instruct

Finetuned
(1036)
this model

Datasets used to train ASSELab/DAT-Llama-3-8B-Instruct

Collection including ASSELab/DAT-Llama-3-8B-Instruct

Papers for ASSELab/DAT-Llama-3-8B-Instruct