An Analysis of Privacy Preservation Techniques in Data Mining

Sachan, Abhishek; Roy, Dhrubojyoti; Arun, P.

doi:10.1007/978-3-642-31600-5_12

Cited by 12 publications

(16 citation statements)

References 20 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In the case of the tMM model, the local summary terms required are (22) above and the following four terms:…”

Section: Private M-stepmentioning

confidence: 99%

“…The first three terms are analogous to (22) to (24), respectively, but with an extra weight variable (k) ijm and the final term is used only for the calculation of (k+1) i .…”

Section: Private M-stepmentioning

confidence: 99%

“…While sending M * A to Party , Party  also sends its learnt quantity (29) to Party . At this stage, Party  is now ready to compute the global sum of (22), which is given by…”

Section: Cycle Twomentioning

confidence: 99%

“…party knows anything except its input and the global results; see also the work of Kumbhar and Kharat 19 for a comparison and analysis of various cryptographic techniques used for privacy preserving association rule mining. For further details, recent surveys on these approaches can be found in the works of Verykios et al, 20 Vaidya, 21 Sachan et al, 22 Matwin, 23 Aldeen et al, 24 and Mendes and Vilela. 25 Mixture models are important and widely popular tools in data mining.…”

mentioning

confidence: 99%

See 3 more Smart Citations

PPEM: Privacy‐preserving EM learning for mixture models

Lee

Leemaqz

McLachlan

2019

Concurrency and Computation

View full text Add to dashboard Cite

Summary Privacy is becoming increasingly important in collaborative data analysis, especially those involving personal or sensitive information commonly arising from health and commercial settings. The aim of privacy preserving statistical algorithms is to allow inference to be drawn on the joint data without disclosing private data held by each party. This paper presents a privacy‐preserving expectation–maximization (PPEM) algorithm for carrying out maximum likelihood estimation of the parameters of mixture models. We address the scenario of horizontally partitioned data distributed among three or more parties. The PPEM algorithm is a two‐cycle iterative distributed algorithm for fitting mixture models under privacy‐preserving requirements. A distinct advantage of PPEM is that it does not require a trusted third party for cooperative learning, unlike most existing schemes that implement a master/slave hierarchy. By adopting a ring topology and adding random noises to messages before encryption, PPEM helps prevent information leakage in the case of corrupted parties. Furthermore, in contrast to existing works, which typically assume a Honest‐but‐Curious adversary, we consider the much stronger case of a Malicious adversary. For illustration, PPEM is applied to two of the most popular mixture models, namely, the normal mixture model (NMM) and t‐mixture model (tMM), and their effectiveness is analyzed through a security analysis. A real data example is also presented to evaluate the computational complexity and accuracy of PPEM relative to its non‐privacy‐preserving version.

show abstract

“…In the case of the tMM model, the local summary terms required are (22) above and the following four terms:…”

Section: Private M-stepmentioning

confidence: 99%

“…The first three terms are analogous to (22) to (24), respectively, but with an extra weight variable (k) ijm and the final term is used only for the calculation of (k+1) i .…”

Section: Private M-stepmentioning

confidence: 99%

“…While sending M * A to Party , Party  also sends its learnt quantity (29) to Party . At this stage, Party  is now ready to compute the global sum of (22), which is given by…”

Section: Cycle Twomentioning

confidence: 99%

mentioning

confidence: 99%

See 2 more Smart Citations

PPEM: Privacy‐preserving EM learning for mixture models

Lee

Leemaqz

McLachlan

2019

Concurrency and Computation

View full text Add to dashboard Cite

show abstract

“…In the reactive approach security agencies try to catch the culprits after the incident to mitigate the effects of the terrorist incident. In both the approaches privacy of the people should be preserve because it cannot be fully compromised for national security as security and privacy are inversely proportional to each other [1]. In counter terrorism the first step after any incident is to find the terrorist group name that might be involved in that particular incident and to make a planned strategy to catch them.…”

Section: Introductionmentioning

confidence: 99%

E-TGPS: Enhanced Terrorist Group Prediction System for Counter Terrorism

Sachan¹

2015

IJCA

Self Cite

View full text Add to dashboard Cite

Terrorist group prediction using historical data of terrorist incidents has been less explored due to the lack of meticulous terrorist data which contains terrorist group's attacks and activities information. There are many reasons for less exploration like its confidentiality & sensitivity. This paper presents an enhanced system that helps to predict the terrorist groups involved in the attack under investigation named E-TGPS. This system initially learns similarities of terrorist activities from various past terrorist incidents to predict the responsible group. This system can be considered as a vital tool for security agencies and intelligence analysts, by providing more reliable and predictive solutions to take effective counterterrorism measures. The system has been validated by experimental results. The overall performance of the system displays a fair degree of accuracy. This paper also lays emphases on the meticulous analysis of optimal parameters weight estimation, to improve the predictive accuracy of the system.

show abstract

Privacy Preserving Data Mining: A Review of the State of the Art

Sharma

Ahuja

2018

Harmony Search and Nature Inspired Optimization Algorithms

View full text Add to dashboard Cite

An Analysis of Privacy Preservation Techniques in Data Mining

Cited by 12 publications

References 20 publications

PPEM: Privacy‐preserving EM learning for mixture models

PPEM: Privacy‐preserving EM learning for mixture models

E-TGPS: Enhanced Terrorist Group Prediction System for Counter Terrorism

Privacy Preserving Data Mining: A Review of the State of the Art

Contact Info

Product

Resources

About