12,789 Hits in 5.2 sec

Continuous Release of Data Streams under both Centralized and Local Differential Privacy [article]

Tianhao Wang, Joann Qiongna Chen, Zhikun Zhang, Dong Su, Yueqiang Cheng, Zhou Li, Ninghui Li, Somesh Jha
2020 arXiv   pre-print
In this paper, we study the problem of publishing a stream of real-valued data satisfying differential privacy (DP).  ...  Within our framework, we design an algorithm satisfying the more stringent setting of DP called local DP (LDP). To our knowledge, this is the first LDP algorithm for publishing streaming data.  ...  To summarize, the main contributions of this paper are threefold: • We design ToPS for releasing real-time data streams under differential privacy.  ... 
arXiv:2005.11753v1 fatcat:3lugkw7xmfaklgjbhmivczfvle

Mobile Privacy-Preserving Crowdsourced Data Collection in the Smart City [article]

Joshua Joy, Ciaran McGoldrick, Mario Gerla
2016 arXiv   pre-print
However, the streaming of big data from IoT devices, especially from mobile platforms like pedestrians and cars, raises significant privacy concerns.  ...  This work proposes a scalable smart city privacy-preserving architecture named Authorized Analytics that enables each node (e.g. vehicle) to divulge (contextually) local privatised data.  ...  To ensure timely results support for stream analytics is desirable. This ensures that data is processed continuously and released on the order of minutes.  ... 
arXiv:1607.02805v1 fatcat:pvwb76e5ifb7za5f7nchorm4ga

Differentially Private Robust Low-Rank Approximation

Raman Arora, Vladimir Braverman, Jalaj Upadhyay
2018 Neural Information Processing Systems  
We propose an algorithm that guarantees We study extensions to the streaming setting where entries of the matrix arrive in an arbitrary order and output is produced at the very end or continually.  ...  k (A) + ⌧, where kBk p is the entry-wise 'p-norm of B and OPT k (A) := min rank(X)k kA Xk p .  ...  Acknowledgements This research was supported in part by NSF BIGDATA grant IIS-1546482, NSF BIGDATA grant IIS-1838139, NSF Career CCF-1652257, and ONR Award N00014-18-1-2364.  ... 
dblp:conf/nips/AroraBU18 fatcat:25k3feqvnvduvjt5v2vdbnypfu

Privacy in Information-Rich Intelligent Infrastructure [article]

Cynthia Dwork, George J. Pappas
2017 arXiv   pre-print
Intelligent infrastructure will critically rely on the dense instrumentation of sensors and actuators that constantly transmit streaming data to cloud-based analytics for real-time monitoring.  ...  meter data, resulting not only in loss of privacy but potentially also putting us at risk.  ...  Acknowledgements Thanks to Rakesh Vohra, Aaron Roth, and Andreas Haeberlen at the University of Pennsylvania for discussions on the privacy of IoT data, and to Helen Wright for invaluable help in writing  ... 
arXiv:1706.01985v1 fatcat:mbu7xn2honhndimxgp5t6mz434

PAS-MC: Privacy-preserving Analytics Stream for the Mobile Cloud [article]

Josh Joy, Mario Gerla
2016 arXiv   pre-print
This paper introduces PAS-MC, the first practical privacy-preserving and anonymity stream analytics system.  ...  In today's digital world, personal data is being continuously collected and analyzed without data owners' consent and choice.  ...  to the local differential privacy mechanism.  ... 
arXiv:1604.04892v1 fatcat:7jlfkxxscngindcmbj2ybidgri

Pan-Private Uniformity Testing [article]

Kareem Amin, Matthew Joseph, Jieming Mao
2020 arXiv   pre-print
In contrast, a locally differentially private algorithm may only access data through public interaction with data holders, and this interaction must be a differentially private function of the data.  ...  Unlike a centrally private algorithm, the algorithm receives data one element at a time and must maintain a differentially private internal state while processing this stream.  ...  These improved the presentation, statements, and proofs of several of our results.  ... 
arXiv:1911.01452v3 fatcat:phe2floccvgj5ogfbabygxwfci

A One-Pass Private Sketch for Most Machine Learning Tasks [article]

Benjamin Coleman, Anshumali Shrivastava
2020 arXiv   pre-print
Inspired by recent progress toward general-purpose data release algorithms, we propose a private sketch, or small summary of the dataset, that supports a multitude of machine learning tasks including regression  ...  Our sketch consists of randomized contingency tables that are indexed with locality-sensitive hashing and constructed with an efficient one-pass algorithm.  ...  We use the MatLab code released by [26] and report the mean squared error (MSE) on a held-out test set in Figure 4 .  ... 
arXiv:2006.09352v1 fatcat:btryq2ftjnad7jyasj7wqrx2oi

Mobility Data Analysis and Applications: A mid-year 2021 Survey [article]

Abhishek Singh, Alok Mathur, Alka Asthana, Juliet Maina, Jade Nester, Sai Sri Sathya, Santanu Bhattacharya, Vidya Phalke
2021 arXiv   pre-print
In this work we review recent works analyzing mobility data and its application in understanding the epidemic dynamics for the COVID-19 pandemic and more.  ...  We also discuss privacy-preserving solutions to analyze the mobility data in order to expand its reach towards a wider population.  ...  There are variants of differential privacy that operate under different threat models like local differential privacy [35] that do not require a trusted and centralized aggregator of the data sources  ... 
arXiv:2109.07901v1 fatcat:3cz7cyw42bagldq4eax4jdcddq

Application of Personal Information Privacy Protection Based on Machine Learning Algorithm

Fang Lang, Yunfei Zhong, Xin Ning
2022 Computational Intelligence and Neuroscience  
parameter updating strategy of joint machine learning under privacy protection are designed.  ...  And, means and reference value is provided for the development direction of privacy protection.  ...  A local differential privacy data stream protection protocol is proposed that can provide data stream privacy while also ensuring high data availability and requiring less storage and computing power.  ... 
doi:10.1155/2022/6710631 pmid:35958767 pmcid:PMC9357731 fatcat:6bgvh25f6bh7vcwcqkqfkbcsji

An Efficient and Scalable Privacy Preserving Algorithm for Big Data and Data Streams

M.A.P. Chamikara, P. Bertok, D. Liu, S. Camtepe, I. Khalil
2019 Computers & security  
We propose a new data perturbation algorithm, SEAL (Secure and Efficient data perturbation Algorithm utilizing Local differential privacy), based on Chebyshev interpolation and Laplacian noise, which provides  ...  The incremental and fast nature of data generation in these systems necessitates scalable privacy-preserving mechanisms with high privacy and utility.  ...  Local Differential Privacy Global differential privacy (GDP) and local differential privacy (LDP) are the two main approaches to differential privacy.  ... 
doi:10.1016/j.cose.2019.101570 fatcat:x57ucwcgibb4pf3qgcn7cditpu

DPCrowd: Privacy-preserving and Communication-efficient Decentralized Statistical Estimation for Real-time Crowd-sourced Data

Xuebin Ren, Chia-Mu Yu, Wei Yu, Xinyu Yang, Jun Zhao, Shusen Yang
2020 IEEE Internet of Things Journal  
Despite no raw data sharing, the real-time statistics could still expose the data privacy of crowd-sourcing participants.  ...  Then, with further consideration of spatial correlations, we develop an enhanced algorithm, DPCrowd+, to deal with multi-dimensional infinite crowd-data streams.  ...  Nonetheless, besides privacy concerns, continuous multi-hop broadcast incurs both tremendous communication overhead and high delay. • Real-time data release.  ... 
doi:10.1109/jiot.2020.3020089 fatcat:qwycqcrhkjai3gk2tnnndkznzy

Security and privacy for big data: A systematic literature review

Boel Nelson, Tomas Olovsson
2016 2016 IEEE International Conference on Big Data (Big Data)  
With big data processing, analyses can be carried out on huge amounts of user data.  ...  In order to have access to real world use cases, we have studied privacy-preserving big data analysis in the context of the automotive domain.  ...  Thus, vehicular data is comprised of both dynamic, continuously growing, data as well as static data.  ... 
doi:10.1109/bigdata.2016.7841037 dblp:conf/bigdataconf/NelsonO16 fatcat:uiippetep5ea3ote2gzsxd5acm

PREDICT: Privacy and Security Enhancing Dynamic Information Collection and Monitoring

Li Xiong, Vaidy Sunderam, Liyue Fan, Slawomir Goryczka, Layla Pournajaf
2013 Procedia Computer Science  
The overall aim of the project is to develop a framework with algorithms and mechanisms for privacy and security enhanced dynamic data collection, aggregation, and analysis with feedback loops.  ...  In this paper, we present an overview of our ongoing project PREDICT (Privacy and secuRity Enhancing Dynamic Information Collection and moniToring).  ...  Acknowledgement This research is supported by the Air Force Office of Scientific Research (AFOSR) DDDAS program under grant FA9550-12-1-0240.  ... 
doi:10.1016/j.procs.2013.05.367 fatcat:5qchd5jl2vhkzdysuqpghyo2pu

Efficient data perturbation for privacy preserving and accurate data stream mining

M.A.P. Chamikara, P. Bertok, D. Liu, S. Camtepe, I. Khalil
2018 Pervasive and Mobile Computing  
Existing privacy preservation methods cannot provide a good balance between data utility and privacy, and also have problems with efficiency and scalability.  ...  P^2RoCAl offers better data utility than similar methods: classification accuracies of P^2RoCAl perturbed data streams are very close to those of the original data streams.  ...  Global differential privacy (GDP) and local differential privacy (LDP) are the two models that can be used to achieve DP over data.  ... 
doi:10.1016/j.pmcj.2018.05.003 fatcat:6qai6rh3dzf3lnr4gty6pllxcq

Private Graph Data Release: A Survey [article]

Yang Li, Michael Purcell, Thierry Rakotoarivelo, David Smith, Thilina Ranbaduge, Kee Siong Ng
2022 arXiv   pre-print
of the limitations of Differential Privacy.  ...  Many of these mechanisms are natural extensions of the Differential Privacy framework to graph data, but we also investigate more general privacy formulations like Pufferfish Privacy that address some  ...  The proposed approach first identifies a small number of important data points from an entire data stream, perturbs these points under local differential privacy, and then reports the perturbed data to  ... 
arXiv:2107.04245v2 fatcat:54bvnswpnbfffiqd5ee5opfope
« Previous Showing results 1 — 15 out of 12,789 results