Accession Number:

AD1058547

Title:

A Game Theoretic Framework for Adversarial Classification

Descriptive Note:

Technical Report,27 Sep 2012,26 Sep 2015

Corporate Author:

University of Texas at Dallas Richardson United States

Personal Author(s):

• Kantarcioglu,Murat
• Xi,Bowei
• Thuraisingham,Bhavani

Report Date:

2017-05-08

Pagination or Media Count:

25.0

Abstract:

Many real world applications, ranging from spam filtering to intrusion detection, are facing malicious adversaries who actively transform the objects under their control to avoid detection. Unfortunately, traditional machine learning techniques are insufficient to handle such adversarial problems directly. Adversaries change the dynamics in standard settings where machine learning techniques are designed to excel. They adopt their attacks to deceive the machine learning models built using the past data.

Descriptors:

• game theory
• machine learning
• data mining
• probability
• data set
• kernel functions
• test sets
• algorithms
• big data
• bayesian networks
• intrusion detection
• classification

Subject Categories:

• Operations Research

Distribution Statement:

APPROVED FOR PUBLIC RELEASE