A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
Filters
Optimal Differentially Private Mechanisms for Randomised Response
2017
IEEE Transactions on Information Forensics and Security
Preserved Fulltext
Other Versions
We examine a generalised Randomised Response (RR) technique in the context of differential privacy and examine the optimality of such mechanisms. ...
Strict and relaxed differential privacy are considered for binary outputs. By examining the error of a statistical estimator, we present closed solutions for the optimal mechanism(s) in both cases. ...
OPTIMAL MECHANISM FOR -DIFFERENTIAL PRIVACY Using the results of Section IV, we can now establish results on the optimal randomised response mechanism for differential privacy. ...
doi:10.1109/tifs.2017.2718487
fatcat:w3fu2tfdufcjdkmhxy4bimvhvi
On Privacy and Accuracy in Data Releases (Invited Paper)
2020
International Conference on Concurrency Theory
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
Finally we illustrate the trade-off between accuracy and privacy for local and oblivious differentially private mechanisms in terms of inference attacks on medium-scale datasets. ...
We show that, where correlations exist in datasets, it is not possible to implement optimal noise-adding mechanisms that give the best possible accuracy or the best possible privacy in all situations. ...
Definition 11 . 11 An -differentially private mechanism M for datasets D(S×U) is optimal wrt. inference attacks on S, if V S [Π M ] ≤ V S [Π M ] for all Π ∈ D(S×U) and all -differentially private mechanisms ...
doi:10.4230/lipics.concur.2020.1
dblp:conf/concur/AlvimFMN20
fatcat:2orz6scuevbutjlrqaahbry4om
Differentially private response mechanisms on categorical data
2016
Discrete Applied Mathematics
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2019; you can also visit the original URL.
The file type is application/pdf.
We study mechanisms for differential privacy on finite datasets. ...
By deriving sufficient sets for differential privacy we obtain necessary and sufficient conditions for differential privacy, a tight lower bound on the maximal expected error of a discrete mechanism and ...
The previous result describes an optimal randomised response mechanism for what is referred to as local differential privacy in [12] . ...
doi:10.1016/j.dam.2016.04.010
fatcat:b7bbnobckrcizarkk7lxjacb7y
Fairly Private Through Group Tagging and Relation Impact
[article]
2021
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2021; you can also visit the original URL.
The file type is application/pdf.
For the count report generation, the aggregator uses TF-IDF to add noise for providing longitudinal Differential Privacy guarantee. ...
Lastly, the mechanism boosts the utility through risk minimization function and obtain the optimal privacy-utility budget of the system. ...
Methodology The goal of work is to develop an unbiased secured mechanism bringing fairness which is also differentially private. ...
arXiv:2105.07244v1
fatcat:utxgfxtuprho7hk6yhojdywnaq
The Bounded Laplace Mechanism in Differential Privacy
2019
Journal of Privacy and Confidentiality
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
We also present a robust method to compute the optimal mechanism parameters to achieve differential privacy in such a setting. ...
The Laplace mechanism is the workhorse of differential privacy, applied to many instances where numerical data is processed. ...
private scale parameter for the bounded Laplace mechanism. ...
doi:10.29012/jpc.715
fatcat:ioqd4nqrobgwvng53vgcjdu5du
Pain-Free Random Differential Privacy with Sensitivity Sampling
[article]
2017
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
Popular approaches to differential privacy, such as the Laplace and exponential mechanisms, calibrate randomised smoothing through global sensitivity of the target non-private function. ...
As an alternative, we propose a straightforward sampler for estimating sensitivity of non-private mechanisms. ...
Consider any non-private mapping f : D n → B, any sensitivity-induced ( , δ)-differentially private mechanism M ∆ mapping B to (randomised) responses in R, any database D of n records, privacy parameters ...
arXiv:1706.02562v1
fatcat:ah3vks2ymjh2lcxsvhfcfwl55m
Learning With Differential Privacy
[article]
2020
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
Other Versions
Differential privacy comes to the rescue with a proper promise of protection against leakage, as it uses a randomized response technique at the time of collection of the data which promises strong privacy ...
The current adaption of differential privacy by leading tech companies and academia encourages authors to explore the topic in detail. ...
It also helps to understand how to introduce noise at the time of data collection or structured surveys by enlightening us on the concepts of Randomized response, Laplace mechanism, Exponential mechanism ...
arXiv:2006.05609v2
fatcat:n4jjarymtvh6toedskl26f66fi
k-Means SubClustering: A Differentially Private Algorithm with Improved Clustering Quality
[article]
2023
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2023; you can also visit the original URL.
The file type is application/pdf.
These DP mechanisms do not guarantee convergence of differentially private iterative algorithms and degrade the quality of the cluster. ...
The existing approaches adapt the method to compute differentially private(DP) centroids by iterative Llyod's algorithm and perturbing the centroid with various DP mechanisms. ...
Anirban Dasgupta (IIT Gandhinagar) for his continuous support and guidance throughout the research. ...
arXiv:2301.02896v1
fatcat:da2zq7gx2zaarf44erhq5schxa
Uniformity Testing in the Shuffle Model: Simpler, Better, Faster
[article]
2021
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2021; you can also visit the original URL.
The file type is application/pdf.
Other Versions
central differential privacy (DP), local privacy (LDP), pan-privacy, and, very recently, the shuffle model of differential privacy. ...
Over the past years, a line of work has been focusing on uniformity testing under privacy constraints on the data, and obtained private and data-efficient algorithms under various privacy models such as ...
Generalised Hadamard Response. We start by recalling the "generalised Hadamard Response" (GHR) mechanism from [11] . ...
arXiv:2108.08987v2
fatcat:mzarcifg3fevrb2672337bftbq
Differentially Private Response Mechanisms on Categorical Data
[article]
2015
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
We study mechanisms for differential privacy on finite datasets. ...
By deriving sufficient sets for differential privacy we obtain necessary and sufficient conditions for differential privacy, a tight lower bound on the maximal expected error of a discrete mechanism and ...
Differential privacy We now define what it means for a response mechanism in our framework to be differentially private. ...
arXiv:1505.07254v1
fatcat:lwjheow2hzaupgpo6lxbrmcrvy
Differential Privacy for Multi-armed Bandits: What Is It and What Is Its Cost?
[article]
2020
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
Other Versions
We observe that the dependency is weaker when we do not require local differential privacy for the rewards. ...
Based on differential privacy (DP) framework, we introduce and unify privacy definitions for the multi-armed bandit algorithms. ...
A privacy-preserving mechanism M composed with a randomised algorithm π : D → A is ǫ-differentially private if for all inputs x, x ′ ∈ D with x − x ′ H = 1: π(A | x) ≤ π(A | x ′ )e ǫ , A ⊂ A. ...
arXiv:1905.12298v2
fatcat:eiv2s4b7yrgajjr2vl3m6z2udi
Fair and Private Rewarding in a Coalitional Game of Cybersecurity Information Sharing
2019
IET Information Security
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2022; you can also visit the original URL.
The file type is application/pdf.
To this end, the sharing system should be equipped with a rewarding and participation-fees allocation mechanisms to encourage sharing behaviour. ...
Moreover, as the participation-fees may leak sensitive information about the organisations' cyber-infrastructure, they study the application of differential privacy in the coalitional game theory to protect ...
Fig. 3 3 Fig. 3 Algorithm 1: Randomised algorithm for finding the differentially private reward value
Fig. 4 4 Fig. 4 Algorithm 2: Randomised algorithm for finding the differentially private reward value ...
doi:10.1049/iet-ifs.2018.5079
fatcat:za6eciaaefdhfeodk7cddnmy44
Robust and Private Bayesian Inference
[chapter]
2014
Lecture Notes in Computer Science
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2017; you can also visit the original URL.
The file type is application/pdf.
We then prove bounds on the robustness of the posterior, introduce a posterior sampling mechanism, show that it is differentially private and provide finite sample bounds for distinguishability-based privacy ...
First, we generalise the concept of differential privacy to arbitrary dataset distances, outcome spaces and distribution families. ...
We gratefully thank Aaron Roth, Kamalika Chaudhuri, and Matthias Bussas for their discussion and insights as well as the anonymous reviewers for their comments on the paper. ...
doi:10.1007/978-3-319-11662-4_21
fatcat:7rxwyiufkbdltg6h7mon7cazt4
BUDS: Balancing Utility and Differential Privacy by Shuffling
[article]
2020
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
private report. ...
Balancing utility and differential privacy by shuffling or BUDS is an approach towards crowd-sourced, statistical databases, with strong privacy and utility balance using differential privacy theory. ...
. • The introduction of risk function for balancing the differential trade-offs and choosing the optimal randomization scheme. ...
arXiv:2006.04125v1
fatcat:agsv43ecrjakxevnd6b4gt74gy
Realistic Differentially-Private Transmission Power Flow Data Release
[article]
2021
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2021; you can also visit the original URL.
The file type is application/pdf.
This protects power flow data for the transmission high-voltage networks, using differentially private transformations that maintain the optimal power flow consistent with, and faithful to, expected model ...
For the modeling, design and planning of future energy transmission networks, it is vital for stakeholders to access faithful and useful power flow data, while provably maintaining the privacy of business ...
step by step; 4) Immunity to post-processing, i.e. any transformations to the output of a differentially private mechanism will produce results that remain differentially private. ...
arXiv:2103.14036v1
fatcat:qpdkzgsozncptmaf2ua3yrawhq
« Previous
Showing results 1 — 15 out of 7,946 results