On Using Linear Diophantine Equations to Tune the extent of Look Ahead while Hiding Decision Tree Rules

TL;DR

This paper introduces a novel method using linear Diophantine equations to determine the extent of lookahead in decision tree rule hiding, aiming to preserve data privacy with minimal impact on data utility.

Contribution

It proposes a new lookahead approach employing linear Diophantine equations to optimize instance addition for privacy-preserving decision tree induction.

Findings

Effective hiding of sensitive rules while maintaining data utility

Minimal disturbance to node entropy achieved

Method outperforms heuristic approaches in preserving data quality

Abstract

This paper focuses on preserving the privacy of sensitive pat-terns when inducing decision trees. We adopt a record aug-mentation approach for hiding sensitive classification rules in binary datasets. Such a hiding methodology is preferred over other heuristic solutions like output perturbation or crypto-graphic techniques - which restrict the usability of the data - since the raw data itself is readily available for public use. In this paper, we propose a look ahead approach using linear Diophantine equations in order to add the appropriate number of instances while minimally disturbing the initial entropy of the nodes.