# Prompt Fuzzing for Fuzz Driver Generation

arXiv: https://arxiv.org/abs/2312.17677 · HTML: https://mlsanity.com/paper/2312.17677/

## Key facts

- Cited by 27 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 29 Dec 2023.

## Built on by (most cited first, 27 of 27)

- [SEC-bench: Automated Benchmarking of LLM Agents on Real-World Software Security Tasks](https://mlsanity.com/paper/2506.11791/) (2025)
- [LLMs in Software Security: A Survey of Vulnerability Detection Techniques and Insights](https://mlsanity.com/paper/2502.07049/) (2025)
- [VulnLLM-R: Specialized Reasoning LLM with Agent Scaffold for Vulnerability Detection](https://mlsanity.com/paper/2512.07533/) (2025)
- [ADMIT: Few-shot Knowledge Poisoning Attacks on RAG-based Fact Checking](https://mlsanity.com/paper/2510.13842/) (2025)
- [Locus: Agentic Predicate Synthesis for Directed Fuzzing](https://mlsanity.com/paper/2508.21302/) (2025)
- [When Fuzzing Meets LLMs: Challenges and Opportunities](https://mlsanity.com/paper/2404.16297/) (2024)
- [Evaluating LLM-Based Regression Test Generation](https://mlsanity.com/paper/2501.11086/) (2025)
- [HarnessAgent: Scaling Automatic Fuzzing Harness Construction with Tool-Augmented LLM Pipelines](https://mlsanity.com/paper/2512.03420/) (2025)
- [PBFuzz: Agentic Directed Fuzzing for PoV Generation](https://mlsanity.com/paper/2512.04611/) (2025)
- [FuzzAug: Data Augmentation by Coverage-guided Fuzzing for Neural Test Generation](https://mlsanity.com/paper/2406.08665/) (2024)
- [LibLMFuzz: LLM-Augmented Fuzz Target Generation for Black-box Libraries](https://mlsanity.com/paper/2507.15058/) (2025)
- [FalseCrashReducer: Mitigating False Positive Crashes in OSS-Fuzz-Gen Using Agentic AI](https://mlsanity.com/paper/2510.02185/) (2025)
- [deepSURF: Detecting Memory Safety Vulnerabilities in Rust Through Fuzzing LLM-Augmented Harnesses](https://mlsanity.com/paper/2506.15648/) (2025)
- [R1-Fuzz: Specializing Language Models for Textual Fuzzing via Reinforcement Learning](https://mlsanity.com/paper/2509.20384/) (2025)
- [Agentic Fuzzing: Opportunities and Challenges](https://mlsanity.com/paper/2605.10074/) (2026)
- [AgentExecutor: Partial Code Execution via Agentic Context Generation](https://mlsanity.com/paper/2608.05959/) (2026)
- [The Greatness of Science Cannot Be Planned: Agentic Auto-Research is Fuzz Testing](https://mlsanity.com/paper/2608.09855/) (2026)
- [Towards Reliable LLM-Driven Fuzz Testing: Vision and Road Ahead](https://mlsanity.com/paper/2503.00795/) (2025)
- [Orion: Fuzzing Workflow Automation](https://mlsanity.com/paper/2509.15195/) (2025)
- [Semantic-Aware Fuzzing: An Empirical Framework for LLM-Guided, Reasoning-Driven Input Mutation](https://mlsanity.com/paper/2509.19533/) (2025)
- [Coverage-Guided Multi-Agent Harness Generation for Java Library Fuzzing](https://mlsanity.com/paper/2603.08616/) (2026)
- [Fuzzing with Agents? Generators Are All You Need](https://mlsanity.com/paper/2604.01442/) (2026)
- [FuzzAgent: Multi-Agent System for Evolutionary Library Fuzzing](https://mlsanity.com/paper/2605.14431/) (2026)
- [Code-Augur: Agentic Vulnerability Detection via Specification Inference](https://mlsanity.com/paper/2606.18619/) (2026)
- [Chai: Agentic Discovery of Cryptographic Misuse Vulnerabilities](https://mlsanity.com/paper/2606.26933/) (2026)
- [Invariant Pretraining for Robust Code Representations](https://mlsanity.com/paper/2608.15412/) (2026)
- [SyzHarness: Patch-Based Kernel Bug Reproduction with LLM-Synthesized Fuzzing Harnesses](https://mlsanity.com/paper/2609.23889/) (2026)

## Abstract (arXiv)

Crafting high-quality fuzz drivers not only is time-consuming but also requires a deep understanding of the library. However, the state-of-the-art automatic fuzz driver generation techniques fall short of expectations. While fuzz drivers derived from consumer code can reach deep states, they have limited coverage. Conversely, interpretative fuzzing can explore most API calls but requires numerous attempts within a large search space. We propose PromptFuzz, a coverage-guided fuzzer for prompt fuzzing that iteratively generates fuzz drivers to explore undiscovered library code. To explore API usage in fuzz drivers during prompt fuzzing, we propose several key techniques: instructive program generation, erroneous program validation, coverage-guided prompt mutation, and constrained fuzzer scheduling. We implemented PromptFuzz and evaluated it on 14 real-world libraries. Compared with OSS-Fuzz and Hopper (the state-of-the-art fuzz driver generation tool), fuzz drivers generated by PromptFuzz achieved 1.61 and 1.63 times higher branch coverage than those by OSS-Fuzz and Hopper, respectively. Moreover, the fuzz drivers generated by PromptFuzz detected 33 genuine, new bugs out of a total of 49 crashes, out of which 30 bugs have been confirmed by their respective communities.