Privacy-Preserving Naive Bayesian Classification

Abstract

Privacy is an important issue in data mining and knowledge discovery. In this paper, we propose to use the randomized response techniques to conduct the data mining computation. Specifically, we present a method to build naive Bayesian classifiers from the disguised data. We conduct experiments to compare the accuracy of our classifier with the one built from the original undisguised data. Our results show that although the data are disguised, our method can still achieve fairly high accuracy.

Open PDF

Document Details

Document Type
Technical Report
Publication Date
Jan 01, 2004
Accession Number
ADA464290

Entities

People

  • Liwu Chang
  • Stan Matwin
  • Zhijun Zhan

Organizations

  • Syracuse University

Tags

Communities of Interest

  • Autonomy
  • Counter IED
  • Materials and Manufacturing Processes

DTIC Thesaurus Topics

  • Accumulators
  • Accuracy
  • Algorithms
  • Artificial Intelligence
  • Artificial Intelligence Software
  • Bayesian Networks
  • Classification
  • Computations
  • Computer Science
  • Data Analysis
  • Data Mining
  • Data Sets
  • Databases
  • Information Science
  • Machine Learning
  • Models
  • Probability

Fields of Study

  • Computer science

Readers

  • Agent-Based Social Robotics and Mobile-Assisted Learning in Virtual Environments.
  • Regression Analysis.

Technology Areas

  • AI & ML
  • AI & ML - Bayesian Inference
  • AI & ML - Machine Learning Algorithms