LearnAFL is a knowledge-learn evolutionary fuzzer based on AFL(American Fuzzy Lop) and is written and maintained by Tai Yue <[email protected]> or <[email protected]>. LearnAFL does not require any prior knowledge of the application or input format. It can learn partial knowledge of some paths by analyzing the test cases that exercise the paths.

LearnAFL: Greybox Fuzzing with Knowledge Enhancement, IEEE Access

LearnAFL requires python 2.7 to call the python script to learn knowledge. Other requirements are as same as those of AFL.

The steps of installing and running LearnAFL are also as same as those of AFL.