mlsanityData to 7 Oct 2026

SeedAIchemy: LLM-Driven Seed Corpus Generation for Fuzzing

arXiv 2511.12448 ↗First posted 16 Nov 2025cs.CR cs.AIcited by 1

Not on the map. Why?

Abstract (arXiv)

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.

Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Builds on 16 of its 38 references that are in the map. First posted on arXiv 16 Nov 2025.

Builds on

16 of 38 references.

References · 16

  1. 2018The Art, Science, and Engineering of Fuzzing: A Surveycited by 61
  2. 2018Evaluating Fuzz Testingcited by 29
  3. 2017Learn&Fuzz: Machine Learning for Input Fuzzingcited by 23
  4. 2020Magma: A Ground-Truth Fuzzing Benchmarkcited by 16
  5. 2024Fuzzing BusyBox: Leveraging LLM and Crash Reuse for Embedded Bug Unearthingcited by 15
  6. 2025Low-Cost and Comprehensive Non-textual Input Fuzzing with LLM-Synthesized Input Generatorscited by 10
  7. 2019A systematic review of fuzzing based on machine learning techniquescited by 8
  8. 2024SoK: Prudent Evaluation Practices for Fuzzingcited by 8
  9. 2024Harnessing Large Language Models for Seed Generation in Greybox Fuzzingcited by 8
  10. 2019A Review of Machine Learning Applications in Fuzzingcited by 4
  11. 2018SmartSeed: Smart Seed Generation for Efficient Fuzzingcited by 3
  12. 2024SyzRetrospector: A Large-Scale Retrospective Study of Syzbotcited by 3
4 more
  1. 2025BugsRepo: A Comprehensive Curated Dataset of Bug Reports, Comments and Contributors Information from Bugzillacited by 3
  2. 2018Semantic Fuzzing with Zestcited by 2
  3. 2017Faster Fuzzing: Reinitialization with Deep Neural Modelscited by 1
  4. 2024ISC4DGF: Enhancing Directed Grey-box Fuzzing with LLM-Driven Initial Seed Corpus Generationcited by 1

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2026: 1.

1 paper.

  1. 2026Inverting the Shield: Systematically Generating Safety Tests from Policy Specificationscited by 0