AFLTurbo: Speed up Path Discovery for Greybox Fuzzing
Lei Sun, Xumei Li, Haipeng Qu, Xiaoshuai Zhang · 2020
Coverage-based greybox fuzzing (CGF) is a common method utilizing coverage information to guide fuzzing. American Fuzzy Lop (AFL) is one of the most famous CGF fuzzers and has been used to uncover thousands of vulnerabilities in many software. However, AFL has two major drawbacks, which impedes it from boosting path discovery: (1) aggressively growing mutation overhead; (2) ineffective mutation region selection. In this paper, we propose three new approaches to overcome the drawbacks: (1) Interruptible mutation, which uses a hang monitor to avoid unnecessary mutation overhead; (2) Locality-based mutation, which utilizes mutation information in previous rounds to guide fuzzing useful regions in future rounds; (3) Hotspot-aware fuzzing, which exploits a pre-evaluation process to identify metadata and only mutates these regions. We combine these approaches into a tool named AFLTurbo based on AFL 2.52b. Furthermore, the effectiveness of AFLTurbo is evaluated in terms of both path discovery and bug detection on eight programs as well as LAVA-M with state-of-the-art fuzzers. The experimental results manifest that AFLTurbo can find 141%, 101% and 41% more paths, and reveal 14×, 30× and 5× more bugs than AFL, AFLFast and FairFuzz respectively. Additionally, AFLTurbo discovers 20 vulnerabilities, of which 18 are assigned with CVEs.