RL-based fuzzer

AntTech

Nov 7, 2022 · Blockchain

Effectively Generating Vulnerable Transaction Sequences in Smart Contracts with Reinforcement Learning‑Guided Fuzzing

This paper presents a reinforcement‑learning‑based fuzzer (RLF) that generates transaction sequences likely to trigger smart‑contract vulnerabilities, combining vulnerability‑driven and coverage‑driven rewards to improve detection efficiency and outperform existing state‑of‑the‑art tools.