SeedAIchemy: LLM-Driven Seed Corpus Generation for Fuzzing
By: Aidan Wen , Norah A. Alzahrani , Jingzhi Jiang and more
Potential Business Impact:
Creates better computer test data automatically.
We introduce SeedAIchemy, an automated LLM-driven corpus generation tool that makes it easier for developers to implement fuzzing effectively. SeedAIchemy consists of five modules which implement different approaches at collecting publicly available files from the internet. Four of the five modules use large language model (LLM) workflows to construct search terms designed to maximize corpus quality. Corpora generated by SeedAIchemy perform significantly better than a naive corpus and similarly to a manually-curated corpus on a diverse range of target programs and libraries.
Similar Papers
LLAMA: Multi-Feedback Smart Contract Fuzzing Framework with LLM-Guided Seed Generation
Software Engineering
Finds hidden bugs in computer money code.
Fuzzwise: Intelligent Initial Corpus Generation for Fuzzing
Software Engineering
Finds software bugs faster using smart AI.
Fuzzing: Randomness? Reasoning! Efficient Directed Fuzzing via Large Language Models
Software Engineering
Finds software bugs much faster.