36,272 Hits in 6.7 sec

Comparing Population Means under Local Differential Privacy: with Significance and Power [article]

Bolin Ding, Harsha Nori, Paul Li, Joshua Allen
2018 arXiv   pre-print
In this paper, we study how to conduct hypothesis tests to compare population means while preserving privacy.  ...  level) and type-II errors (1 - power).  ...  The second one has provable significance and lower bounds of power, and it can be extended for population with hybrid privacy requirements.  ... 
arXiv:1803.09027v1 fatcat:dllkflxrprhb5luiwtofgaej5e

XYZ Privacy [article]

Josh Joy, Dylan Gray, Ciaran McGoldrick, Mario Gerla
2018 arXiv   pre-print
Future autonomous vehicles will generate, collect, aggregate and consume significant volumes of data as key gateway devices in emerging Internet of Things scenarios.  ...  The quality and usability of such privatized data will lie at the heart of future safe and efficient transportation solutions. In this paper, we present the XYZ Privacy mechanism.  ...  Thus, these type of local differentially private protocols are best suited for tracking heavy-hitters (e.g., counting the most commonly occurring elements in peaky power-law distributions) [3] .  ... 
arXiv:1710.03322v5 fatcat:sxodr5x6bzhktezpus6plglnly

The Philosophy of Differential Privacy

Claire McKay Bowen, Simson Garfinkel
2021 Notices of the American Mathematical Society  
Local differential privacy. Local differential privacy does not have a trusted curator.  ...  Google's experience with integrating differential privacy into the Chrome web browser shows both the promise and real-world limitations of local differential privacy.  ... 
doi:10.1090/noti2363 fatcat:pe2ri2ukynf7hhkeonvnwxhpvq

Per-instance Differential Privacy

Yu-Xiang Wang
2019 Journal of Privacy and Confidentiality  
We consider a refinement of differential privacy --- per instance differential privacy (pDP), which captures the privacy of a specific individual with respect to a fixed data set.  ...  We consider a refinement of differential privacy --- per instance differential privacy (pDP), which captures the privacy of a specific individual with respect to a fixed data set.  ...  We also thank the journal editor and anonymous reviewers for their helpful feedbacks that lead to significant improvements of the paper.  ... 
doi:10.29012/jpc.662 fatcat:7ypap7anbnc5dhd2acjg64m3ha

Federated Heavy Hitters Discovery with Differential Privacy [article]

Wennan Zhu, Peter Kairouz, Brendan McMahan, Haicheng Sun, Wei Li
2020 arXiv   pre-print
Finally, we carefully compare our approach to Apple's local differential privacy method for discovering heavy hitters.  ...  A significant advantage of this approach is that it eliminates the need to centralize raw data while also avoiding the significant loss in utility incurred by local differential privacy.  ...  experiments on real data and compare to local differential privacy.  ... 
arXiv:1902.08534v4 fatcat:ymcshac2tvca5ieyxoshqv6eky

Privacy analytics

Hamed Haddadi, Richard Mortier, Steven Hand
2012 Computer communication review  
We acknowledge feedback from Claude Castelluccia and anonymous reviewers.  ...  of individuals leads to a distributed form of differential privacy [9] .  ...  Human proximity information is collected from the general population using phones with Bluetooth communication, to build time dependent contact networks.  ... 
doi:10.1145/2185376.2185390 fatcat:fa6emusj7zdxtjd3zgx5fkdxve

The Cost of Privacy: Optimal Rates of Convergence for Parameter Estimation with Differential Privacy [article]

T. Tony Cai, Yichen Wang, Linjun Zhang
2020 arXiv   pre-print
In this paper, we investigate the tradeoff between statistical accuracy and privacy in mean estimation and linear regression, under both the classical low-dimensional and modern high-dimensional settings  ...  A primary focus is to establish minimax optimality for statistical estimation with the (ε,δ)-differential privacy constraint.  ...  minimax rates with the α-local privacy constraint; [40] proved several minimax optimal rates of convergence under α-local differential privacy and exhibited a mechanism that is minimax optimal for linear  ... 
arXiv:1902.04495v5 fatcat:2lgz6mtdafdj3occdv6owz6aoe

A Statistical Overview on Data Privacy [article]

Fang Liu
2020 arXiv   pre-print
In addition to legal policies and regulations, technological tools and statistical strategies also exist to promote and safeguard individual privacy, while releasing and sharing useful population-level  ...  privacy protection and information sharing.  ...  Extension of Classical Differential Privacy Local Differential Privacy One of the population extensions of the classical DP is the so-called local DP. 24 Formally, local DP bounds the likelihood ratio  ... 
arXiv:2007.00765v1 fatcat:n2elnyxchfdj7hdxxyofaycxoe

Per-instance Differential Privacy [article]

Yu-Xiang Wang
2018 arXiv   pre-print
We consider a refinement of differential privacy --- per instance differential privacy (pDP), which captures the privacy of a specific individual with respect to a fixed data set.  ...  The result reveals an interesting and intuitive fact that an individual has stronger privacy if he/she has small "leverage score" with respect to the data set and if he/she can be predicted more accurately  ...  We also thank the editor and anonymous reviewers for their helpful feedbacks that lead to significant improvements of the paper.  ... 
arXiv:1707.07708v4 fatcat:icpv4ohakffazm7budks6dglau

Learning With Differential Privacy [article]

Poushali Sengupta, Sudipta Paul, Subhankar Mishra
2020 arXiv   pre-print
The different aspects of differential privacy, it's application in privacy protection and leakage of information, a comparative discussion, on the current research approaches in this field, its utility  ...  The current adaption of differential privacy by leading tech companies and academia encourages authors to explore the topic in detail.  ...  reports with localized differential privacy guarantee.  ... 
arXiv:2006.05609v2 fatcat:n4jjarymtvh6toedskl26f66fi

Subset Privacy: Draw from an Obfuscated Urn [article]

Ganghua Wang, Jie Ding
2021 arXiv   pre-print
With the rapidly increasing ability to collect and analyze personal data, data privacy becomes an emerging concern.  ...  In this work, we develop a new statistical notion of local privacy to protect each categorical data that will be collected by untrusted entities.  ...  The above features distinguish subset privacy with (local) differential privacy and its variants. 2) Rigorous privacy guarantee.  ... 
arXiv:2107.02013v1 fatcat:cwqcykk2rzbuho32vnvm7o3e3y

Systematizing Genome Privacy Research: A Privacy-Enhancing Technologies Perspective [article]

Alexandros Mittos and Bradley Malin and Emiliano De Cristofaro
2018 arXiv   pre-print
However, this also prompts a number of security and privacy concerns stemming from the distinctive characteristics of genomic data.  ...  Finally, we report on the importance and difficulty of the identified challenges based on an online survey of genome data privacy experts  ...  This research was partially supported by the European Union's Horizon 2020 Research and Innovation program under the Marie Skłodowska-Curie "Privacy&Us" project (GA No. 675730), a Google Faculty Award  ... 
arXiv:1712.02193v2 fatcat:2pdqmdfv3nhfjbuyn3kwmudija

A Comprehensive Survey on Local Differential Privacy

Xingxing Xiong, Shubo Liu, Dan Li, Zhaohui Cai, Xiaoguang Niu
2020 Security and Communication Networks  
Local differential privacy (LDP) is a state-of-the-art privacy preservation technique that allows to perform big data analysis (e.g., statistical estimation, statistical learning, and data mining) while  ...  ., frequency estimation and mean estimation) and complex statistical estimation (e.g., multivariate distribution estimation and private estimation over complex data) under LDP.  ...  local privacy by constraining the adversaries' power and proposed a two-pronged approach for locally differentially private Federated Learning with the smaller privacy parameter ε and obtained high-performance  ... 
doi:10.1155/2020/8829523 fatcat:xjk3vgyambb5xioc2q5hyr2hua

Types of Privacy Expectations

Ashwini Rao, Juergen Pfeffer
2020 Frontiers in Big Data  
Inspired by expectations-related theory in non-privacy literature, we propose a conceptual model of privacy expectation with four distinct types - Desired, Predicted, Deserved and Minimum.  ...  About one third of the population rates the Predicted and Minimum expectation types differently, and differences are more pronounced between younger (18-29 years) and older (60+ years) population.  ...  The authors thank Florian Schaub and Birendra Jha for their helpful feedback.  ... 
doi:10.3389/fdata.2020.00007 pmid:33693382 pmcid:PMC7931868 fatcat:di73alpnefa5tlqin5dxinrtma

Risks of Privacy-Enhancing Technologies: Complexity and Implications of Differential Privacy in the Context of Cybercrime [chapter]

William Stadler
2020 Security and Privacy From a Legal, Ethical, and Technical Perspective  
The chapter concludes with a discussion of several practical considerations related to the use of Differential Privacy as a tool in the fight against cybercrime and offers recommendations for future research  ...  Combined with an increase in the frequency and prevalence of cybercrime, more of the public now face the very real risk of privacy loss associated with illegitimate use of private data.  ...  There is also a significant need and opportunity for cross-disciplinary collaboration with respect to cybercrime and privacy-related research.  ... 
doi:10.5772/intechopen.92752 fatcat:zgyalic6y5f4pi443ybtxdbmjy
« Previous Showing results 1 — 15 out of 36,272 results