meta-pytorch / opacus
Training PyTorch models with differential privacy
Why this job: works in the areas we cover, but does not say which job it does
What it does
Opacus is a library that enables training PyTorch models with differential privacy. It supports training with minimal code changes required on the client, has little impact on training performance, and allows the client to online track the privacy budget expended at any given moment.
Get started
pip install opacus- Maintenance
- Active
- Last commit 49 days ago
- Stars
- 1,970
- On GitHub
- Licence
- Apache-2.0
- Allows business use
- Downloads for
- None listed
- No release files
- Latest version
- v1.6.0
- Released 6 months ago
- Built with
- Python
- 50% of the code
Is it looked after?
- Contributors
- Not stated
- Last 90 days
- Issues
- 82% closed
- 63 still open
- Pull requests
- 59 merged
- 22 waiting
- Releases
- 27
- 1 in the last year
- Contributing guide (opens in new tab)
- No security policy
- Code of conduct (opens in new tab)
Similar repos
| Repo | Stars | Last commit | Licence | Downloads for |
|---|---|---|---|---|
| IBM / differential-privacy-library | 921 | 6 days ago | MIT | No downloads |
| mosaicml / streaming | 1,571 | 9 days ago | Apache-2.0 | No downloads |
| apple / pfl-research | 359 | 22 days ago | Apache-2.0 | No downloads |
More: languages, topics and project record
Languages
- Python 50%
- Jupyter Notebook 47%
- CSS 2%
- JavaScript 1%
Topics
- differential-privacy
- privacy-preserving-machine-learning
- deep-learning
- machine-learning
- neural-network
- pytorch
Project record
- JobOther AI tools
- StatusListed
- Commits814
- Forks402
- Watching40
- Stars in 28 days+4
- CreatedDec 7, 2019
- First seen by usNov 7, 2026
- CheckedNov 8, 2026