Paper Detail

FunFuzz: An LLM-Powered Evolutionary Fuzzing Framework

Mario Rodríguez Béjar, B. Romera-Paredes, Jose L. Hernández-Ramos

arxiv Score 8.2

Published 2026-05-04 · First seen 2026-05-05

General AI

Abstract

Modern fuzzers increasingly use Large Language Models (LLMs) to generate structured inputs, but LLM-driven fuzzing is sensitive to prompt initialization and sampling variance, which can reduce exploration efficiency and lead to redundant inputs. We present FunFuzz, a multi-island evolutionary fuzzing framework that runs several isolated searches in parallel and periodically migrates high-value candidates to maintain diversity. FunFuzz derives initial generation prompts from documentation and initializes islands with topic-specific instructions, then continuously adapts prompts using feedback-guided selection. During fuzzing, candidates are prioritized by incremental compiler coverage, while compiler-internal failure signals are used to identify crash-inducing inputs. We evaluate FunFuzz on compiler fuzzing, where inputs are source programs and success is measured by compiler coverage and unique compiler-internal failures. Across repeated 24-hour campaigns on GCC and Clang, FunFuzz achieves higher compiler coverage than previous LLM-driven baselines and discovers more unique failure-triggering inputs.

Workflow Status

Review status
pending
Role
unreviewed
Read priority
soon
Vote
Not set.
Saved
no
Collections
Not filed yet.
Next action
Not filled yet.

Reading Brief

No structured notes yet. Add `summary_sections`, `why_relevant`, `claim_impact`, or `next_action` in `papers.jsonl` to enrich this view.

Why It Surfaced

No ranking explanation is available yet.

Tags

No tags.

BibTeX

@article{bjar2026funfuzz,
  title = {FunFuzz: An LLM-Powered Evolutionary Fuzzing Framework},
  author = {Mario Rodríguez Béjar and B. Romera-Paredes and Jose L. Hernández-Ramos},
  year = {2026},
  abstract = {Modern fuzzers increasingly use Large Language Models (LLMs) to generate structured inputs, but LLM-driven fuzzing is sensitive to prompt initialization and sampling variance, which can reduce exploration efficiency and lead to redundant inputs. We present FunFuzz, a multi-island evolutionary fuzzing framework that runs several isolated searches in parallel and periodically migrates high-value candidates to maintain diversity. FunFuzz derives initial generation prompts from documentation and ini},
  url = {https://arxiv.org/abs/2605.02789},
  keywords = {cs.CR, cs.CL},
  eprint = {2605.02789},
  archiveprefix = {arXiv},
}

Metadata

{}