mlsanityData to 7 Oct 2026

Towards Reliable LLM-Driven Fuzz Testing: Vision and Road Ahead

arXiv 2503.00795 ↗First posted 2 Mar 2025cs.SE cs.AIcited by 0

Not on the map. Why?

Abstract (arXiv)

Fuzz testing is a crucial component of software security assessment, yet its effectiveness heavily relies on valid fuzz drivers and diverse seed inputs. Recent advancements in Large Language Models (LLMs) offer transformative potential for automating fuzz testing (LLM4Fuzz), particularly in generating drivers and seeds. However, current LLM4Fuzz solutions face critical reliability challenges, including low driver validity rates and seed quality trade-offs, hindering their practical adoption. This paper aims to examine the reliability bottlenecks of LLM-driven fuzzing and explores potential research directions to address these limitations. It begins with an overview of the current development of LLM4SE and emphasizes the necessity for developing reliable LLM4Fuzz solutions. Following this, the paper envisions a vision where reliable LLM4Fuzz transforms the landscape of software testing and security for industry, software development practitioners, and economic accessibility. It then outlines a road ahead for future research, identifying key challenges and offering specific suggestions for the researchers to consider. This work strives to spark innovation in the field, positioning reliable LLM4Fuzz as a fundamental component of modern software testing.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 23 of its 74 references that are in the map. First posted on arXiv 2 Mar 2025.

Builds on

23 of 74 references.

References · 23

  1. 2023GPT-4 Technical Reportcited by 18,132
  2. 2020Retrieval-Augmented Generation for Knowledge-Intensive NLP Taskscited by 9,160
  3. 2023Retrieval-Augmented Generation for Large Language Models: A Surveycited by 2,185
  4. 2023Code Llama: Open Foundation Models for Codecited by 2,105
  5. 2020CodeBERT: A Pre-Trained Model for Programming and Natural Languagescited by 1,286
  6. 2023StarCoder: may the source be with you!cited by 790
  7. 2022InCoder: A Generative Model for Code Infilling and Synthesiscited by 492
  8. 2022UniXcoder: Unified Cross-Modal Pre-training for Code Representationcited by 355
  9. 2023BLIVA: A Simple Multimodal LLM for Better Handling of Text-Rich Visual Questionscited by 125
  10. 2023Automatic Semantic Augmentation of Language Model Prompts (for Code Summarization)cited by 72
  11. 2018The Art, Science, and Engineering of Fuzzing: A Surveycited by 61
  12. 2024A Deep Dive into Large Language Models for Automated Bug Localization and Repaircited by 39
11 more
  1. 2023Prompt Fuzzing for Fuzz Driver Generationcited by 27
  2. 2023How Effective Are They? Exploring Large Language Model Based Fuzz Driver Generationcited by 21
  3. 2023Augmenting Greybox Fuzzing with Generative AIcited by 18
  4. 2022Fuzzing Deep-Learning Libraries via Automated Relational API Inferencecited by 16
  5. 2024Fuzzing BusyBox: Leveraging LLM and Crash Reuse for Embedded Bug Unearthingcited by 15
  6. 2023Understanding Programs by Exploiting (Fuzzing) Test Casescited by 13
  7. 2022Open Problems in Fuzzing RESTful APIs: A Comparison of Toolscited by 5
  8. 2021IntelliGen: Automatic Driver Synthesis for FuzzTestingcited by 3
  9. 2022BeDivFuzz: Integrating Behavioral Diversity into Generator-based Fuzzingcited by 3
  10. 2021The Good, The Bad and The Missing: A Narrative Review of Cyber-security Implications for Australian Small Businessescited by 2
  11. 2024ProphetFuzz: Fully Automated Prediction and Fuzzing of High-Risk Option Combinations with Only Documentation via Large Language Modelcited by 2

Built on by

Not cited yet.