Publication Date

Spring 2017

Degree Type

Master's Project

Degree Name

Master of Science (MS)


Computer Science

First Advisor

Thomas Austin

Second Advisor

Robert Chun

Third Advisor

James Casaletto


Taint Analysis, Information Flow Security


Web application systems today are at great risk from attackers. They use methods like cross-site scripting, SQL injection, and format string attacks to exploit vulnerabilities in an application. Standard techniques like static analysis, code audits seem to be inadequate in successfully combating attacks like these. Both the techniques point out the vulnerabilities before an application is run. However, static analysis may result in a higher rate of false positives, and code audits are time-consuming and costly. Hence, there is a need for reliable detection mechanisms.

Dynamic taint analysis offers an alternate solution — it marks the incoming data from the untrusted source as ‘tainted.’’ The flow of tainted data is tracked during the program execution. Whenever tainted data is used in a security-sensitive context, a proper action is taken. The execution may also be suspended depending upon the severity of the operation.

This project implements dynamic taint analysis in Rhino JavaScript. The focus is on adding support for coarse-grained and fine-grained string tainting. Coarse-grained tainting works at the granularity level of a string while fine-grained tainting works at the granularity level of a character in a string. Both approaches are discussed in further detail in the paper. I have also written a SQL library to leverage my implementation of taint analysis in Rhino and conducted performance tests to contrast the overhead of coarse & fine grained taint analysis. My test results show that fine-grained taint analysis in general incurs more overhead than coarse-grained taint analysis.