Privacy preservation for Neural Network Training
Journal Title: International Journal of Computer Science & Engineering Technology - Year 2014, Vol 5, Issue 6
Abstract
Data mining enables us to extract interesting patterns from huge volumes of data. This can be a security/privacy issue, if we make sensitive information available to unintended users as a result of mining. Preserving the privacy of sensitive data and individuals' information is a major challenge in many applications. Privacy concerns may prevent the parties from directly sharing the data and some types of information about the data. Back propagation (BP) is one of the algorithms used for training neural networks. This algorithm is suitable for both single-layer and multi-layer models. Another neural network training algorithm values for weights. Training the network is achieved by iteratively adjusting the weights based on a set of input parameters. During this process a training sample is presented to the network and is forwarded to determine the resulting output. The difference between the obtained output and expected output in each output unit represents error. Error is back propagated is the Extreme Learning Machine (ELM) algorithm. This algorithm works only for single-layer models. This restriction makes ELM more efficient than BP by reducing the communication between multiple parties during the learning phase. Most of the neural network learning systems is designed for single-layer and multi-layer models which can be applied to continuous data and differentiable activation functions. The present work proposes a protocol for neural network training systems that guarantee data confidentiality when data is partitioned among several parties. The proposed protocol preserves the privacy of both the input data and the constructed learning model.
Authors and Affiliations
Ms. Ch. Aparna , Ms. K. Venkata Ramana
Keywords
Related Articles
- EP ID EP116128
- DOI -
- Views 93
- Downloads 0
A Comparative Study of Various Network Simulation Tools
In the area of network research, establishing a network in a real time scenario is very difficult. A single test bed takes a large amount of time and cost. Thus a network simulator tool helps the network developer to che...
Emblematic Fuzzy C-means Clustering for Demographic Dataset
Clustering algorithms are very useful in the field of marketing, education, and healthcare and engineering. It has several advantages such as -it deals with different type of data (text, numerical, image, categorical.),h...
SURVEY OF ACCIDENT SEVERITY ESTIMATION USING DATA MINING TECHNIQUES
As technology has been improved by many changes and inventions are made almost every day. Traumatic events come in many different ways at many different times of one’s life. Recent trends on the advantage of communicatio...
A Novel Approach for Web Document Classification
The web is a huge repository of information and there is a need for categorizing web documents to facilitate the search and retrieval of documents. Web document classification plays an important role in information organ...
Applications of Finite Automata in Lexical Analysis and as a Ticket Vending Machine – A Review
In this paper, we explain the two applications of finite automata. First is about the first phase of a compiler design called as lexical analysis. The lexical analysis used to identify the token with its type. Second is...