• Journal of KIISE
• /
• v.44 no.2
• /
• pp.171-178
• /
• 2017

In this study, we propose an automated unit test generation technique for detecting vulnerabilities of Android kernel modules. The technique automatically generates unit test drivers/stubs and unit test inputs for each function of Android kernel modules by utilizing dynamic symbolic execution. To reduce false alarms caused by function pointers and missing pre-conditions of automated unit test generation technique, we develop false alarm reduction techniques that match function pointers by utilizing static analysis and generate pre-conditions by utilizing def-use analysis. We showed that the proposed technique could detect all existing vulnerabilities in the three modules of Android kernel 3.4. Also, the false alarm reduction techniques removed 44.9% of false alarms on average.

• Journal of Software Engineering Society
• /
• v.23 no.4
• /
• pp.141-149
• /
• 2010

Agile development is mentioned a lot by developers these days. XP or Scrum is one of the popular development processes, and it says that unit test automation would drive an agile development successful. The success of unit test automation depends on how well to compare an execution result to its own expected result. that is why this paper focuses on the comparison part. This paper introduces how to build test codes for unit testing, and then concludes with mentioning two considerations of unit testing automation. First, test codes for void-typed methods need Mock Framework to monitor their behavior. Second, the comparison of execution results and expected results is hard to implement in case of testing void-typed methods. We check every sentences of a test path to decide if the testing is fail or pass.