# Low-Cost and Comprehensive Non-textual Input Fuzzing with LLM-Synthesized Input Generators

arXiv: https://arxiv.org/abs/2501.19282 · HTML: https://mlsanity.com/paper/2501.19282/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 31 Jan 2025.

## Built on by (most cited first, 10 of 10)

- [Frontier AI's Impact on the Cybersecurity Landscape](https://mlsanity.com/paper/2504.05408/) (2025)
- [VulnLLM-R: Specialized Reasoning LLM with Agent Scaffold for Vulnerability Detection](https://mlsanity.com/paper/2512.07533/) (2025)
- [IP Leakage Attacks Targeting LLM-Based Multi-Agent Systems](https://mlsanity.com/paper/2505.12442/) (2025)
- [Reasoning as a Resource: Optimizing Fast and Slow Thinking in Code Generation Models](https://mlsanity.com/paper/2506.09396/) (2025)
- [R1-Fuzz: Specializing Language Models for Textual Fuzzing via Reinforcement Learning](https://mlsanity.com/paper/2509.20384/) (2025)
- [SeedAIchemy: LLM-Driven Seed Corpus Generation for Fuzzing](https://mlsanity.com/paper/2511.12448/) (2025)
- [Rethinking and Exploring String-Based Malware Family Classification in the Era of LLMs and RAG](https://mlsanity.com/paper/2507.04055/) (2025)
- [Once4All: Skeleton-Guided SMT Solver Fuzzing with LLM-Synthesized Generators](https://mlsanity.com/paper/2508.20340/) (2025)
- [LLMs + Security = Trouble](https://mlsanity.com/paper/2602.08422/) (2026)
- [ABTest: Behavior-Driven Testing for AI Coding Agents](https://mlsanity.com/paper/2604.03362/) (2026)

## Abstract (arXiv)

Modern software often accepts inputs with highly complex grammars. Recent advances in large language models (LLMs) have shown that they can be used to synthesize high-quality natural language text and code that conforms to the grammar of a given input format. Nevertheless, LLMs are often incapable or too costly to generate non-textual outputs, such as images, videos, and PDF files. This limitation hinders the application of LLMs in grammar-aware fuzzing. We present a novel approach to enabling grammar-aware fuzzing over non-textual inputs. We employ LLMs to synthesize and also mutate input generators, in the form of Python scripts, that generate data conforming to the grammar of a given input format. Then, non-textual data yielded by the input generators are further mutated by traditional fuzzers (AFL++) to explore the software input space effectively. Our approach, namely G2FUZZ, features a hybrid strategy that combines a holistic search driven by LLMs and a local search driven by industrial quality fuzzers. Two key advantages are: (1) LLMs are good at synthesizing and mutating input generators and enabling jumping out of local optima, thus achieving a synergistic effect when combined with mutation-based fuzzers; (2) LLMs are less frequently invoked unless really needed, thus significantly reducing the cost of LLM usage. We have evaluated G2FUZZ on a variety of input formats, including TIFF images, MP4 audios, and PDF files. The results show that G2FUZZ outperforms SOTA tools such as AFL++, Fuzztruction, and FormatFuzzer in terms of code coverage and bug finding across most programs tested on three platforms: UNIFUZZ, FuzzBench, and MAGMA.