Privacy-preserving distributed k-means clustering over arbitrarily partitioned data

Jagannathan, Geetha; Wright, Rebecca N.

doi:10.1145/1081870.1081942

Cited by 331 publications

(182 citation statements)

References 10 publications

Supporting

Mentioning

176

Contrasting

Unclassified

Order By: Relevance

“…There is a demand for efficient solutions, perhaps with provable approximations, in practice. In the past two years, a number of such protocols have been designed and analyzed in theory and database community; see [188] and examples of [10,97,141,202] for a sample of recent developments.…”

Section: Privacy Preserving Data Miningmentioning

confidence: 99%

Data Streams: Algorithms and Applications

Muthukrishnan

2005

FNT in Theoretical Computer Science

769

541

View full text Add to dashboard Cite

In the data stream scenario, input arrives very rapidly and there is limited memory to store the input. Algorithms have to work with one or few passes over the data, space less than linear in the input size or time significantly less than the input size. In the past few years, a new theory has emerged for reasoning about algorithms that work within these constraints on space, time, and number of passes. Some of the methods rely on metric embeddings, pseudo-random computations, sparse approximation theory and communication complexity. The applications for this scenario include IP network traffic analysis, mining text message streams and processing massive data sets in general. Researchers in Theoretical Computer Science, Databases, IP Networking and Computer Systems are working on the data stream challenges. This article is an overview and survey of data stream algorithmics and is an updated version of [175].

show abstract

Section: Privacy Preserving Data Miningmentioning

confidence: 99%

Data Streams: Algorithms and Applications

Muthukrishnan

2005

FNT in Theoretical Computer Science

769

541

View full text Add to dashboard Cite

show abstract

“…However, they use classical encryption schemes [8,9]. Elliptic Curve Cryptography (ECC) based approach gives promising results as classical encryption schemes [10,11].…”

Section: S J Patel Et Almentioning

confidence: 99%

Comparative Evaluation of Elliptic Curve Cryptography Based Homomorphic Encryption Schemes for a Novel Secure Multiparty Computation

Patel¹,

Chouhan²,

Jinwala³

2014

JIS

View full text Add to dashboard Cite

In this paper, we focus on Elliptic Curve Cryptography based approach for Secure Multiparty Computation (SMC) problem. Widespread proliferation of data and the growth of communication technologies have enabled collaborative computations among parties in distributed scenario. Preserving privacy of data owned by parties is crucial in such scenarios. Classical approach to SMC is to perform computation using Trusted Third Party (TTP). However, in practical scenario, TTPs are hard to achieve and it is imperative to eliminate TTP in SMC. In addition, existing solutions proposed for SMC use classical homomorphic encryption schemes such as RSA and Paillier. Due to the higher cost incurred by such cryptosystems, the resultant SMC protocols are not scalable. We propose Elliptic Curve Cryptography (ECC) based approach for SMC that is scalable in terms of computational and communication cost and avoids TTP. In literature, there do exist various ECC based homomorphic schemes and it is imperative to investigate and analyze these schemes in order to select the suitable for a given application. In this paper, we empirically analyze various ECC based homomorphic encryption schemes based on performance metrics such as computational cost and communication cost. We recommend an efficient algorithm amongst several selected ones, that offers security with lesser overheads and can be applied in any application demanding privacy.

show abstract

“…For example, both a university and a hospital may collect information about a student. Again, secure protocols for the vertically partitioned case have been developed for mining association rules [35], and k-means clusters [16,34]. All of those previous protocols claimed to be secure only in the semi-honest model.…”

Section: Related Workmentioning

confidence: 99%

Privacy-Preserving Data Mining: A Game-Theoretic Approach

Miyaji

Rahman

2011

Lecture Notes in Computer Science

View full text Add to dashboard Cite

Abstract. Privacy-preserving data mining has been an active research area in recent years due to privacy concerns in many distributed data mining settings. Protocols for privacy-preserving data mining have considered semi-honest, malicious, and covert adversarial models in cryptographic settings, whereby an adversary is assumed to follow, arbitrarily deviate from the protocol, or behaving somewhere in between these two, respectively. Semi-honest model provides weak security requiring small amount of computation, on the other hand, malicious and covert models provide strong security requiring expensive computations like homomorphic encryptions. However, game theory allows us to design protocols where parties are neither honest nor malicious but are instead viewed as rational and are assumed (only) to act in their own self-interest. In this paper, we build efficient and secure set-intersection protocol in gametheoretic setting using cryptographic primitives. Our construction avoids the use of expensive tools like homomorphic encryption and oblivious transfer. We also show that our protocol satisfies computational versions of strict Nash equilibrium and stability with respect to trembles.

show abstract

Privacy-preserving distributed k-means clustering over arbitrarily partitioned data

Cited by 331 publications

References 10 publications

Data Streams: Algorithms and Applications

Data Streams: Algorithms and Applications

Comparative Evaluation of Elliptic Curve Cryptography Based Homomorphic Encryption Schemes for a Novel Secure Multiparty Computation

Privacy-Preserving Data Mining: A Game-Theoretic Approach

Contact Info

Product

Resources

About