Filters








9,949 Hits in 3.6 sec

Differentially-Private Multi-Party Sketching for Large-Scale Statistics

Seung Geol Choi, Dana Dachman-soled, Mukul Kulkarni, Arkady Yerukhimovich
2020 Proceedings on Privacy Enhancing Technologies  
and obtain a general framework for constructing multi-party differentially private protocols for several other sketching algorithms.  ...  Next, we show how to eliminate this requirement of a private hash function by injecting a small amount of noise, allowing us to instantiate an efficient LogLog protocol for the multi-party setting.  ...  Differentially private multi-party LogLog algorithm.  ... 
doi:10.2478/popets-2020-0047 fatcat:tuadgjwozrfrtdcgmvocxmqsnq

Efficient Privacy-Preserving Machine Learning for Blockchain Network

Hyunil Kim, Seung-Hyun Kim, Jung Yeon Hwang, Changho Seo
2019 IEEE Access  
Our model can treat any type of differentially private learning algorithm where non-deterministic functions should be defined.  ...  We develop a differentially private stochastic gradient descent method and an error-based aggregation rule as core primitives.  ...  In addition, on the system security side, computation in a distributed network with multi-party entities sometimes incurs system failure by computational error.  ... 
doi:10.1109/access.2019.2940052 fatcat:snkur6qmnzctvh3kbew5zx2czi

Flatee: Federated Learning Across Trusted Execution Environments [article]

Arup Mondal and Yash More and Ruthu Hulikal Rooparaghunath and Debayan Gupta
2021 arXiv   pre-print
Several approaches have been proposed to overcome this, based on multi-party computation, fully homomorphic encryption, etc.; many of these protocols are slow and impractical for real-world use as they  ...  Federated learning allows us to distributively train a machine learning model where multiple parties share local model parameters without sharing private data.  ...  Multi-party computation has been used for privacy-preserving ML [12] .  ... 
arXiv:2111.06867v1 fatcat:rl2rysly7fcbtnw32acea4liu4

Rmind: A Tool for Cryptographically Secure Statistical Analysis

Dan Bogdanov, Liina Kamm, Sven Laur, Ville Sokk
2018 IEEE Transactions on Dependable and Secure Computing  
Secure multi-party computation platforms are becoming more and more practical. This has paved the way for privacy-preserving statistical analysis using secure multi-party computation.  ...  We give descriptions of the privacy-preserving algorithms and benchmark results that show the feasibility of our solution.  ...  For secure multi-party computation, the main threat is that computing parties collude to reveal private inputs.  ... 
doi:10.1109/tdsc.2016.2587623 fatcat:7iw65bregfeaxn44eaew4nwhem

Optimal Lower Bound for Differentially Private Multi-party Aggregation [chapter]

T-H. Hubert Chan, Elaine Shi, Dawn Song
2012 Lecture Notes in Computer Science  
We consider distributed private data analysis, where n parties each holding some sensitive data wish to compute some aggregate statistics over all parties' data.  ...  Our lower bounds generalize to the ( , δ) differential privacy notion, for reasonably small values of δ.  ...  They prove that any differentially-private multi-party protocol with a small number of rounds and small number of messages must have large error.  ... 
doi:10.1007/978-3-642-33090-2_25 fatcat:d2nxboaryzhmbh4rlqorkwlzoa

Private record matching using differential privacy

Ali Inan, Murat Kantarcioglu, Gabriel Ghinita, Elisa Bertino
2010 Proceedings of the 13th International Conference on Extending Database Technology - EDBT '10  
Private matching can be solved securely and accurately using secure multi-party computation (SMC) techniques, but such an approach is prohibitively expensive in practice.  ...  Private matching between datasets owned by distinct parties is a challenging problem with several applications.  ...  Two main approaches have been proposed for private matching: sanitization methods and Secure Multi-party Computation (SMC) protocols [14] .  ... 
doi:10.1145/1739041.1739059 dblp:conf/edbt/InanKGB10 fatcat:t35ybo453vetzkrxrhri63t4gy

Privacy-Preserving Statistical Data Analysis on Federated Databases [chapter]

Dan Bogdanov, Liina Kamm, Sven Laur, Pille Pruulmann-Vengerfeldt, Riivo Talviste, Jan Willemson
2014 Lecture Notes in Computer Science  
We describe an implementation on two real-world platforms-the Sharemind secure multi-party computation and the X-Road database federation platform.  ...  In this paper, we propose a novel way to combine secure multi-party computation technology with federated database systems to preserve privacy in statistical studies that combine and analyse data from  ...  Development The authors wish to thank the interviewees for their time and cooperation and the Estonian Center for Applied Research for their help in generating the artificial data used in the experiments of  ... 
doi:10.1007/978-3-319-06749-0_3 fatcat:uvfasioddjfgflnn3px2xw54nu

Distributed Anonymization: Achieving Privacy for Both Data Subjects and Data Providers [chapter]

Pawel Jurczyk, Li Xiong
2009 Lecture Notes in Computer Science  
There is an increasing need for sharing data repositories containing personal information across multiple distributed and private databases.  ...  However, such data sharing is subject to constraints imposed by privacy of individuals or data subjects as well as data confidentiality of institutions or data providers.  ...  Secure multi-party computation. Our approach also has its roots in the secure multi-party computation (SMC) problem [7, 8, 9, 10, 11] .  ... 
doi:10.1007/978-3-642-03007-9_13 fatcat:t4y2k2uhkzadhgk63npy4rvy2q

Efficient Private Statistics with Succinct Sketches [article]

Luca Melis and George Danezis and Emiliano De Cristofaro
2016 arXiv   pre-print
of median statistics for Tor hidden services.  ...  In this paper, we present the design and implementation of practical techniques for privately gathering statistics from large data streams.  ...  We would like to thank Chris Newell and Michael Smethurst from the BBC and Aaron Johnson from US Naval Research Labs for motivating our work, respectively, on privacy-preserving recommendation and median  ... 
arXiv:1508.06110v3 fatcat:oqrtjnqvr5hzjjmqxcbpxruoiq

A NOVEL PRIVACY PRESERVATION MECHANISM FOR DATA AND USER IN DISTRIBUTED SERVERS

Dr. D. Suresh, Dr. N. Dhanalakshmi, Dr. A. Thomas Paul Roy
2021 Information Technology in Industry  
The median decision generated with the aid of our algorithms is a hundred twenty five meters.  ...  Anonymity can supply a excessive diploma of privacy, retailer provider customers from dealing with carrier providers' privateness policies, and limit the carrier providers' necessities for safeguarding  ...  D SecureMulti-party Computation (SMC) Secure multi-party computing is a subfield of cryptography (also considered as impenetrable computing, mixed computer (MPC) or computing which preserves privacy) in  ... 
doi:10.17762/itii.v9i1.248 fatcat:webyxcu7xnfutoydtyiprp5hxi

L1 - An Intermediate Language for Mixed-Protocol Secure Computation

Axel Schropfer, Florian Kerschbaum, Gunter Muller
2011 2011 IEEE 35th Annual Computer Software and Applications Conference  
Secure Computation (SC) enables secure distributed computation of arbitrary functions of private inputs. It has many useful applications, e.g. benchmarking or auctions.  ...  We show by three case studies -one for computation of the median, one for weighted average, one for division -that special protocols and mixed-protocol implementations in our language L1 can lead to superior  ...  INTRODUCTION Secure Computation (SC) allows a set of n players P i to jointly compute an arbitrary function f () of their private inputs x i (i.e. P i has x i ): f (x 1 , . . . , x n ).  ... 
doi:10.1109/compsac.2011.46 dblp:conf/compsac/SchropferKM11 fatcat:5wu7l6hs75hobk7f7qzi2f2lzy

Enhancing the Privacy of Federated Learning with Sketching [article]

Zaoxing Liu, Tian Li, Virginia Smith, Vyas Sekar
2019 arXiv   pre-print
practical, private federated learning.  ...  Federated learning methods run training tasks directly on user devices and do not share the raw user data with third parties.  ...  For instance, [10] brings secure multi-party computation (SMC) into federated learning.  ... 
arXiv:1911.01812v1 fatcat:mquqgd2ykjepdidtf5bx4rkkpq

Achieving Security and Privacy in Federated Learning Systems: Survey, Research Challenges and Future Directions [article]

Alberto Blanco-Justicia, Josep Domingo-Ferrer, Sergio Martínez, David Sánchez, Adrian Flanagan, Kuan Eeik Tan
2020 arXiv   pre-print
In contrast with centralized ML approaches, FL saves computation to the server and does not require the clients to outsource their private data to the server. However, FL is not free of issues.  ...  Afterwards, we discuss the difficulty of simultaneously achieving security and privacy protection. Finally, we sketch ways to tackle this open problem and attain both security and privacy.  ...  acknowledge support from Huawei Technologies Oy (Finland) (agreement no YBN2019035188), the European Commission (projects H2020-871042 "SoBigData++" and H2020-101006879 "MobiDataLab"), the Government of  ... 
arXiv:2012.06810v1 fatcat:ipqvco22uraepf7ygmzfso3yy4

On the practical importance of communication complexity for secure multi-party computation protocols

Florian Kerschbaum, Daniel Dahlmeier, Axel Schröpfer, Debmalya Biswas
2009 Proceedings of the 2009 ACM symposium on Applied Computing - SAC '09  
Many advancements in the area of Secure Multi-Party Computation (SMC) protocols use improvements in communication complexity as a justification.  ...  of the network performance.  ...  INTRODUCTION Secure Multi-Party Computation (SMC) protocols offer a general solution for many problems in secure distributed computing, e.g. private auctions or joint database calculations.  ... 
doi:10.1145/1529282.1529730 dblp:conf/sac/KerschbaumDSB09 fatcat:ctuitteornajldfzlzcqtyslnq

Differentially Private Bayesian Learning on Distributed Data [article]

Mikko Heikkilä and Eemil Lagerspetz and Samuel Kaski and Kana Shimizu and Sasu Tarkoma and Antti Honkela
2017 arXiv   pre-print
We propose a learning strategy based on a secure multi-party sum function for aggregating summaries from data holders and the Gaussian mechanism for DP.  ...  We consider DP Bayesian learning in a distributed setting, where each party only holds a single sample or a few samples of the data.  ...  The method is based on a DP secure multi-party communication (SMC) algorithm, called Distributed Compute algorithm (DCA), for achieving DP in the distributed setting.  ... 
arXiv:1703.01106v2 fatcat:tj2z67ax5ndvxfvuxhyu2gefzy
« Previous Showing results 1 — 15 out of 9,949 results