Hybrid Fuzzing with LLM-Guided Input Mutation and Semantic Feedback
Author:
Preprint
- 23 September 2025
- preprint
- Published by MDPI AG in Preprints.org
Abstract
Software fuzzing has become a cornerstone in automated vulnerability discovery, yet existing mutation strategies often lack semantic awareness, leading to redundant test cases and slow exploration of deep program states. In this work, we present a hybrid fuzzing framework that integrates static and dynamic analysis with Large Language Model (LLM)-guided input mutation and semantic feedback. Static analysis extracts control-flow and data-flow information, which is transformed into structured prompts for the LLM to generate syntactically valid and semantically diverse inputs. During execution, we augment traditional coverage-based feedback with semantic feedback signals—derived from program state changes, exception types, and output semantics—allowing the fuzzer to prioritize inputs that trigger novel program behaviors beyond mere code coverage. We implement our approach atop AFL++, combining program instrumentation with embedding-based semantic similarity metrics to guide seed selection. Evaluation on real-world open-source targets, including libpng, tcpdump, and sqlite, demonstrates that our method achieves faster time-to-first-bug, higher semantic diversity, and a competitive number of unique bugs compared to state-of-the-art fuzzers. This work highlights the potential of combining LLM reasoning with semantic-aware feedback to accelerate and deepen vulnerability discovery.Keywords
All Related Versions
This publication has 4 references indexed in Scilit:
- ELFuzz: Efficient Input Generation via LLM-driven Synthesis Over Fuzzer SpacearXiv, 2025
- Harnessing Large Language Models for Seed Generation in Greybox FuzzingarXiv, 2024
- LLAMAFUZZ: Large Language Model Enhanced Greybox FuzzingarXiv, 2024
- Reinforcement Learning Approach for Integrating Compressed Contexts into Knowledge Graphs2024