The objective of software testing is to stress a program to reveal programming defects. Security testing is, more specifically, that branch of testing which aims to reveal defects that could lead to security problems. Most of security testing declinations, however, have been mostly interested in the automatic generation of test cases that "try" to reveal a vulnerability, rather than assessing if test cases have actually "managed" to reveal vulnerabilities.
In this paper, we cope with the latter problem. We investigate on the feasibility of using tree kernel methods to implement a classifier able to evaluate if a test case revealed a vulnerability, i.e. a security oracle for injection attacks. We compare six different variants of tree kernel methods in terms of their effectiveness in detecting attacks.
Link to the paper.