Questions tagged [differential-privacy]

The tag has no usage guidance.

14 questions with no upvoted or accepted answers
Filter by
Sorted by
Tagged with
3
votes
0answers
35 views

Adding Laplace noise to a learned neural network

My question is related to the concept of differential privacy and deep learning. I found many papers to learn neural networks with differential privacy, but is it also possible to achieve differential ...
3
votes
1answer
37 views

Communicating aggregate percentage changes in data without exposing individual contributors

So i have a dataset that tracks widget production from 100 different factories, each individually owned and highly competitive. Each line contains the factory name, the date of production, and the # ...
2
votes
0answers
23 views

What is statistical difference?

In the paper "Calibrating Noise to Sensitivity in Private Data Analysis" by Dwork et al., the term "statistical difference" is used as following (in page 280): Finally, if a $1 − \...
2
votes
0answers
28 views

Interpretation of the ratio of two pdfs evaluated at a certain point?

What is the interpretation of the ratio of two pdfs evaluated at a certain point? Is that a statistical distance? Is there any applications of it? I only know one application of differential privacy, ...
2
votes
0answers
13 views

Can we get the input from a multilayer perceptron based on the output of one of its hidden layers?

I was reading a relatively new paper that proposed to split a nerual networks layers into groups and sending each group to different nodes to train them in a distributed manner. In order to not send ...
2
votes
1answer
164 views

Differential Privacy: why $\delta$ negligible on the row numbers?

The definition of differential privacy says that an algorithm $M$ is $(\epsilon,\delta)$-differentially private if $$P(M(x \in D) \in S)\leq e^\epsilon P(M(x \in D')\in S) + \delta$$ where $D,D'$ ...
1
vote
1answer
21 views

Laplace mechanism on vector record?

Does the definition of neighboring database in differential privacy capture the multi-dimensional record? Let's say we have a database domain $\mathbb{N}^{n\times d}$ where $n$ is the number of ...
1
vote
0answers
30 views

What data is sent from a client to a server in a federated learning setting?

So far, I thought federated learning works like this: All clients have the same machine learning model (if not personalized). They have their unique data and then train this model (e.g., neural ...
1
vote
0answers
66 views

What current methods for statistical disclosure limitation are best trade-offs between data privacy and data utility?

In many situations raw microdata is not released by institutions due to privacy preserving. Many techniques are used for protecting sensitive values in data. But many of them can destroy multivariate ...
0
votes
0answers
7 views

The amount of noise needed for independent vs. dependent features in differential privacy

There is this paper that says: Remark 1. DP noise is applied with the assumption that features are independent from each other, meaning a maximal amount of noise must be applied to each feature to ...
0
votes
0answers
15 views

How to create differentially private synthetic or noisy dataset?

I can view my original dataset as points in n dimensional space, how do I create a differentially private synthetic dataset for such a dataset. You can also think of it as having a dataset with m ...
0
votes
1answer
17 views

Does $\epsilon$-differential privacy treat databases with one record of difference a completely different databases?

Does $\epsilon$-differential privacy treat databases with one record difference completely different database? What I want to know is about continuous release. Suppose we have a set of users and some ...
0
votes
0answers
8 views

How could I implement data binning for differential privacy, similar to Apple's Count Mean Sketch or Hadamard Count Mean Sketch?

I'm looking at the Apple differential privacy document here and it has the paragraph: The noise injection step works as follows: After encoding the input as a vector using a hash function, each ...
0
votes
1answer
374 views

Global sensitivity of mean and variance in differential privacy?

Please explain me why global sensitivity of a mean or variance queries will be (b-a)/n and (b-a)^2/n where b is the upper ...