Sanjay Bapna

A Wavelet-Based Approach to Preserve Privacy for Classification Mining*

Despite the commercial success of data mining, a major drawback has been acknowledged across academic, industry, and government sectors, namely, the issue of violating the privacy of individuals. We propose a data transformation method based on wavelets to disguise private data while preserving the original classification patterns. Wavelet transformations have been used extensively in signal processing for data reduction, multiresolution analysis, and removing noise from data. In our implementation, two commonly used wavelet transforms, the Haar and the Daub-4 transforms, are tested for pattern and privacy preservation in classification mining tasks. Empirical results confirm that the Haar and the Daub-4 transforms preserve the classification patterns and preserve the privacy for real valued data.

The economic impact of cyber terrorism

What is the economic impact of cyber terrorism? Can organizations achieve strategic advantage in the cyber terrorism game? A general game theoretical model is proposed to study the optimal information systems (ISs) security investment and then applied to compare the losses caused by cyber terrorists and common hackers. Literature is reviewed on IS security, game theoretical models of IS security, cyber terrorism, cyber deterrence and IS security breach function. Simulations with varying levels of attackers preference, breach function sensitivity and deterrence level are carried out to determine sensitivity to the optimal IS security investment. Results suggest that organizations should invest more to protect their strategic information systems against cyber terrorists who have long-term goals.

A Web-Based GIS for Analyzing Commercial Motor Vehicle Crashes

The purpose of this paper is to describe the design and implementation of a Web-based geographic information system GIS for providing online crash information and statistical information for commercial vehicle crashes. The system is capable of displaying crash data such as specific geographic location, period and time of crashes, severity, contributing factors, and cost. The system supports interagency communication with the purpose of reducing the number of crashes. Through the description of the design and implementation of the system, we demonstrate the feasibility of addressing spatial problems in a collaborative OLAP environment. It provides a guide for the design and development of similar systems and identifies a series or related, but yet unsolved, research problems.

How Can We Deter Cyber Terrorism

ABSTRACT In order to deter cyber terrorism, it is important to identify the terrorists, since punishment may not deter them. The identification probability relies heavily on tracking cyber terrorists. However, there are legal and technical challenges to tracking terrorists. This paper proposes suggestions and insights on overcoming these challenges. Three types of infrastructures must be present in order to deter cyber terrorism: technical, policy, and legal. We list some of the key items that academics as well as practitioners need to focus on to improve cyber-terrorism deterrence.

Measuring interestingness of discovered skewed patterns in data cubes

This paper describes a methodology of OLAP cube navigation to identify interesting surprises by using a skewness based approach. Three different measures of interestingness of navigation rules are proposed. The navigation rules are examined for their interestingness in terms of their expectedness of skewness from neighborhood rules. A novel Axis Shift Theory (AST) to determine interesting navigation paths is presented along with an attribute influence approach for generalization of rules, which measures the interestingness of dimensional attributes and their relative influence on navigation paths. Detailed examples and extensive experiments demonstrate the effectiveness of interestingness of navigation rules.

Text Mining to Identify Customers Likely to Respond to Cross-Selling Campaigns: Reading Notes from Your Customers

This paper reports on the results of extracting useful information from text notes captured within a Customer Relationship Management (CRM) system to segment and thus target groups of customers likely to respond to cross-selling campaigns. These notes often contain text that is indicative of customer intentions. The results indicate that the notes are meaningful in classifying customers who are likely to respond to purchase multiple communication devices. A Naive Bayes classifier outperformed a Support Vector Machine classifier for this task. When combined with structured information, the classifier performed only marginally better. Thus, customer service notes can be an important source of predictive data in CRM systems.

Navigation Rules for Exploring Large Multidimensional Data Cubes

Navigating through multidimensional data cubes is a nontrivial task. Although On-Line Analytical Processing (OLAP) provides the capability to view multidimensional data through rollup, drill-down, and slicing-dicing, it offers minimal guidance to end users in the actual knowledge discovery process. In this article, we address this knowledge discovery problem by identifying novel and useful patterns concealed in multidimensional data that are used for effective exploration of data cubes. We present an algorithm for the DIscovery of Sk-NAvigation Rules (DISNAR), which discovers the hidden interesting patterns in the form of Sk-navigation rules using a test of skewness on the pairs of the current and its candidate drill-down lattice nodes. The rules then are used to enhance navigational capabilities, as illustrated by our rule-driven system. Extensive experimental analysis shows that the DISNAR algorithm discovers the interesting patterns with a high recall and precision with small execution time and low space overhead.

Who Can We Trust?: The Economic Impact of Insider Threats

Abstract Information Systems (IS) Security has become a critical issue in the IT world. Among all threats against IS security, the insider threat is the greatest. This paper proposes a game theoretical model to study the economic impact of insider threats on IS security investments. We identify three factors influencing the optimal IS security investment: breach function sensitivity, deterrence level, and advantage rate. Our simulation results show that the optimal investment required to protect an information systems infrastructure from insiders is several magnitudes higher than for protecting against external hackers.

Securing computerised models and data against integrity attacks

Many computerised systems use electronic models that get triggered when certain business conditions arise. Unauthorised triggering of such computerised models has been overlooked in the security literature. In this paper, we propose two frameworks to analyse the security of systems that have the data-triggering computerised model architecture. The frameworks help understand how to mitigate the cyber attacks that can be launched against the data-model systems, by modifying the computerised models or the data. We then propose a Deterministic Specification distributed intrusion Detection System (DSdIDS) to secure the data-triggering model systems from internal as well as external cyber threats.

Utilizing Business Intelligence to Enhance Online Education at For-Profit and Non-Profit Institutions

With the increase in the demand of online education, especially for working people, there is a need for institutions that offer online education to identify, target, and market their services to people who are in need of furthering their education or who would be interested in using online education to advance their careers. The aim of this paper is to explore how Business Intelligence (BI) can be utilized to enhance online education for profit and non-profit organizations. The goal is to identify, target, and market online education to an audience who may not have thought of online education, but will appreciate the opportunity.