tensorflow / tensorflow/privacy

Calculating the privacy budget in the absence of additive noise

Open
#136 9 comments 1 reaction 0 assignees View on GitHub

Nobody has claimed this yet.

Dominant language
Python
Stars
2k
Forks
477
Avg merge
22h 12m
Merged PRs (30d)
1

Description

Hello. The "rdp_accountant" code assumes an additive Sampled Gaussian Mechanism (SGM). However, I am interested in calculating the privacy budget (epsilon and delta) when no noise is added. In this case, the privacy is offered by other adjustments on the queries (gradients). Any idea on how to calculate the privacy measures in this case? Many thanks in advance.

Contributor guide

Open the contributing guide

First steps

  1. Read the whole issue, then the project's contributing guide.
  2. Comment on the issue to say you are picking it up — it saves two people doing the same work.
  3. Fork the repository and make your change on a branch.
  4. Open a pull request that references the issue number.

Research direction

Start by reading the rdp_accountant code and its assumptions about the additive Sampled Gaussian Mechanism. Clarify how the query or gradient adjustments provide privacy without additive noise, then define what calculation and validation would count as done for epsilon and delta.

Written by the indexing model from the issue text.

Assessment

Tech stack
python
Domain
machine-learning, security
Issue type
Feature
Difficulty
5/5
Estimated time
Over a week
Activity status
Stale
Clarity
Needs clarification
Newbie friendliness
20/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.