Release MemPrivacy-Bench dataset on Hugging Face

[NielsRogge]

Hi @hush-cd 🤗

I'm Niels and work as part of the open-source team at Hugging Face. I discovered your excellent work through Hugging Face's daily papers as yours got featured: https://huggingface.co/papers/2605.09530.
The paper page lets people discuss about your paper and lets them find artifacts about it (your models or datasets for instance), you can also claim the paper as yours which will show up on your public profile at HF, add Github and project page URLs.

It's great to see that you've already released the MemPrivacy models on https://huggingface.co/models! This helps a lot with discoverability and reproducibility.

I also noticed your paper introduces a new dataset, "MemPrivacy-Bench", which is crucial for evaluating privacy protection strategies. Would you be interested in hosting this dataset on https://huggingface.co/datasets as well?
This would further improve its visibility and enable better discoverability for other researchers. They could easily load it with:

from datasets import load_dataset

dataset = load_dataset("your-hf-org-or-username/your-dataset")

Here's a guide for uploading datasets: https://huggingface.co/docs/datasets/loading.
The dataset viewer also allows people to quickly explore the data in the browser.

After uploading, we can also link the dataset to the paper page (read here) so people can discover your work more easily.

Let me know if you're interested or need any guidance!

Kind regards,

Niels
ML Engineer @ HF 🤗

[hush-cd]

Hi @NielsRogge,

Thank you so much for your kind message and for featuring our work on Hugging Face Daily Papers 🤗 We really appreciate the support from the HF open-source team.

We’re currently organizing and cleaning the MemPrivacy-Bench dataset, including documentation and metadata, to make the release more complete and reproducible for the community. We do plan to upload the dataset to Hugging Face Datasets and open-source it publicly in the near future.

Once the dataset is ready, we’ll also link it to the paper page and project resources accordingly.

Thanks again for the suggestion and guidance — Hugging Face has been incredibly helpful for improving the visibility and accessibility of our work.