Retrospective

Jazzer+LibAFL: Insights into Java Fuzzing

AIxCC involved finding bugs in software written in two languages: C++ and Java. The focus of the competition was on the use of LLMs and AI, however, our teams approach was to balance ambitious strategies alongside proven traditional bug-finding techniques like fuzzing. While our team was deeply familiar with fuzzing C++ from decades of academic research and industry work, Java was uncharted territory for us. In part of our Java fuzzing development we created a fork of Jazzer that uses LibAFL as the fuzzing backend and it is available as part of our open source release. This post details some of the lessons we learned about Java fuzzing and the creation of this fork.