tensorflow / tensorflow/privacy
what is the optimal RDP order?
Open
Nobody has claimed this yet.
- Dominant language
- Python
- Stars
- 2k
- Forks
- 477
- Avg merge
- 22h 12m
- Merged PRs (30d)
- 1
Description
when i use compute_dp_sgd_privacy, it shows this result. I know the epsilon is the strength of the privacy guarantee, but what does optimal RDP order means?
compute_dp_sgd_privacy.compute_dp_sgd_privacy(n=len(training_sequences), batch_size=250, noise_multiplier=1.3, epochs=15, delta=1e-5)
Output:
DP-SGD with sampling rate = 1.67% and noise_multiplier = 1.3 iterated over 900 steps satisfies differential privacy with eps = 2.46 and delta = 1e-05.
The optimal RDP order is 10.0.
(2.4614490035755816, 10.0)
Contributor guide
First steps
- Read the whole issue, then the project's contributing guide.
- Comment on the issue to say you are picking it up — it saves two people doing the same work.
- Fork the repository and make your change on a branch.
- Open a pull request that references the issue number.
Research direction
Start at the compute_dp_sgd_privacy entry point and trace where the reported epsilon and optimal RDP order are calculated and formatted. Review the existing documentation and comments around this output; done means documenting what the optimal RDP order represents and how it relates to the reported privacy guarantee.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- python, tensorflow
- Domain
- machine-learning, security
- Issue type
- Documentation
- Difficulty
- 3/5
- Estimated time
- 1-2 days
- Activity status
- Stale
- Clarity
- Needs clarification
- Newbie friendliness
- 35/100