Skip to main content

Questions tagged [differential-privacy]

Questions about differential privacy, a measure and method for preserving privacy when querying statistical datasets.

Filter by
Sorted by
Tagged with
3 votes
1 answer
209 views

Is the differential privacy definition with lower and upper bound equivalent to the definition with just an upper bound?

According to Wikipedia, given a randomized algorithm $\mathcal{A}$, two neighboring datasets $D_1, D_2$, a real number $\epsilon > 0$, $\mathcal{A}$ provides $\epsilon$-differential privacy, if $$ \...
user3389669's user avatar
3 votes
1 answer
166 views

Differential Privacy with only positive noise

The Laplace mechanism is a standard way of making the output of a function $f$ differentially private. More concretely, let $\Delta_f$ be the sensitivity of $f$, i.e. the maximum value by which the ...
Cryptonaut's user avatar
2 votes
1 answer
95 views

About the definition of "differential privacy" in communication complexity

In the context of communication complexity I see a definition of differential privacy which isn't totally clear to me as to why it makes sense. So the two parties $A$ and $B$ draw two strings $X$ ...
user6818's user avatar
  • 1,145
2 votes
0 answers
61 views

In a machine learning system, why use differentially private SGD if our input data is already perturbed by a DP mechanism?

I'm trying to implement my own version of a deep neural network with differential privacy to preserve the privacy of the parties involved in the training dataset. I'm using the method by Abadi et al. ...
Saam's user avatar
  • 121
1 vote
1 answer
112 views

Histogram representation of a database

I'm reading though The Algorithmic Foundations of Differential Privacy and the authors define a database in a mathematically convenient way. Unfortunately I'm a little confused about what the ...
robtimus_prime's user avatar
1 vote
1 answer
147 views

What is the sensitivity of gradient clipping in Differentially Private SGD?

As far as I understand, the Gaussian Mechanism uses the sensitivity of the input function to determine the right amount of noise. In DP-SGD, said input function is taking the gradient and clipping it ...
arujj's user avatar
  • 13
1 vote
0 answers
26 views

Upper bound via standard manipulation in proof of semi-private learning

I have been reading a paper on private learning [1]. In the proof of lemma 3.3. they claim that $$ 2\left(\frac{2e n_\text{pub}}{d}\right)^{2d}e^{-\alpha n_\text{pub}/4} $$ is upper bounded by $\beta$ ...
TheCollegeStudent's user avatar
0 votes
0 answers
11 views

How can I anonymize/ de-identify clinical data present in tabular format

So I have been tasked to anonymize clinical data that..most of the time would be present in the form of tables. I've looked into algorithms like generalization,redaction,K-anonymity, l-diversity,t-...
S1000's user avatar
  • 1