Towards Efficient and Scalable Training of Differentially Private Deep Learning

(See '/research' for the code used in the benchmarks of our paper).

jaxdpopt package

Install using pip install . with Python>=3.10 in a fresh environment.

Examples can be found in '/examples' and tests can be run after installing pytest with python3 -m pytest ..

Contact

For comments and issues, create a new issue in the repository.

Citation

If you use this code, please cite our paper

@misc{beltran2024efficientscalabletrainingdifferentially,
      title={Towards Efficient and Scalable Training of Differentially Private Deep Learning}, 
      author={Sebastian Rodriguez Beltran and Marlon Tobaben and Joonas J{\"{a}}lk{\"{o}} and Niki Loppi and Antti Honkela},
      year={2024},
      eprint={2406.17298},
      archivePrefix={arXiv},
      primaryClass={cs.LG},
      url={https://arxiv.org/abs/2406.17298}, 
}

Metadata

Release files for jaxdpopt 0.0.1

For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.

Source distribution (sdist)

Source distribution for jaxdpopt 0.0.1
File	Size	Uploaded	Provenance	Actions
jaxdpopt-0.0.1.tar.gz	67.1 kB	Mar 25, 2025	Without provenance	Details for jaxdpopt-0.0.1.tar.gz

Built distribution (wheel)

Table of built distributions (wheels) for jaxdpopt 0.0.1
File	Interpreter	ABI	Platform	Actions Reset
jaxdpopt-0.0.1-py3-none-any.whl 35.4 kB Mar 25, 2025 Without provenance	Python 3	none	any	Details for jaxdpopt-0.0.1-py3-none-any.whl

Total release size: 102.5 kB

Release files / jaxdpopt-0.0.1.tar.gz

Download URL	jaxdpopt-0.0.1.tar.gz
Size	67.1 kB
Tags	Source
SHA-256 checksum How to use checksums	`029c0bd77266f323c8def7c82282e1c5b65d6955e361d484eebe8db496dec114`
BLAKE2b-256 checksum How to use checksums	`acb73ca6a485c36c570b029272f159cba76f75423680734aba21197c1e7fe7a2`
Upload date	Mar 25, 2025
Uploaded using Trusted Publishing? What is trusted publishing?	No
Uploaded via	`twine/6.1.0 CPython/3.12.3`

Release files / jaxdpopt-0.0.1-py3-none-any.whl

Download URL	jaxdpopt-0.0.1-py3-none-any.whl
Size	35.4 kB
Tags	Python 3
SHA-256 checksum How to use checksums	`0d6936b6e623263ebb6b0a7e9c6ddc5fcda2aa3b4d5a4f74eb94b34911a0e788`
BLAKE2b-256 checksum How to use checksums	`34e27fb7592fed1c1ef4498dade1fce1b0d8923e697d523fe697564b320dc6d3`
Upload date	Mar 25, 2025
Uploaded using Trusted Publishing? What is trusted publishing?	No
Uploaded via	`twine/6.1.0 CPython/3.12.3`

Security for jaxdpopt 0.0.1

Report project as malware

Provenance

Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.

No provenance found

None of the files in this release were uploaded with provenance metadata.

A note on package security

PyPI is a repository for distributing packages, not a service for auditing them. While third-party security researchers and our staff do their best to detect and remove malicious packages, PyPI cannot guarantee the quality, security or suitability of any given package.

To learn more about protecting yourself from malicious actors, visit our package security documentation.

Release history Release notifications | RSS feed

This release

0.0.1 This release

Mar 25, 2025 2 release files No provenance

jaxdpopt 0.0.1