Orion: Fuzzing Workflow Automation
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , |
|---|---|
| Format: | Preprint |
| Publié: |
2025
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866912592937615360 |
|---|---|
| author | Bazalii, Max Fleischer, Marius |
| author_facet | Bazalii, Max Fleischer, Marius |
| contents | Fuzz testing is one of the most effective techniques for finding software vulnerabilities. While modern fuzzers can generate inputs and monitor executions automatically, the overall workflow, from analyzing a codebase, to configuring harnesses, to triaging results, still requires substantial manual effort. Prior attempts focused on single stages such as harness synthesis or input minimization, leaving researchers to manually connect the pieces into a complete fuzzing campaign.
We introduce Orion, a framework that automates the the manual bottlenecks of fuzzing by integrating LLM reasoning with traditional tools, allowing campaigns to scale to settings where human effort alone was impractical. Orion uses LLMs for code reasoning and semantic guidance, while relying on deterministic tools for verification, iterative refinement, and tasks that require precision. Across our benchmark suite, Orion reduces human effort by 46-204x depending on the workflow stage, and we demonstrate its effectiveness through the discovery of two previously unknown vulnerabilities in the widely used open-source clib library. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2509_15195 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Orion: Fuzzing Workflow Automation Bazalii, Max Fleischer, Marius Software Engineering Artificial Intelligence Cryptography and Security D.4.6; I.2.2; D.2.5 Fuzz testing is one of the most effective techniques for finding software vulnerabilities. While modern fuzzers can generate inputs and monitor executions automatically, the overall workflow, from analyzing a codebase, to configuring harnesses, to triaging results, still requires substantial manual effort. Prior attempts focused on single stages such as harness synthesis or input minimization, leaving researchers to manually connect the pieces into a complete fuzzing campaign. We introduce Orion, a framework that automates the the manual bottlenecks of fuzzing by integrating LLM reasoning with traditional tools, allowing campaigns to scale to settings where human effort alone was impractical. Orion uses LLMs for code reasoning and semantic guidance, while relying on deterministic tools for verification, iterative refinement, and tasks that require precision. Across our benchmark suite, Orion reduces human effort by 46-204x depending on the workflow stage, and we demonstrate its effectiveness through the discovery of two previously unknown vulnerabilities in the widely used open-source clib library. |
| title | Orion: Fuzzing Workflow Automation |
| topic | Software Engineering Artificial Intelligence Cryptography and Security D.4.6; I.2.2; D.2.5 |
| url | https://arxiv.org/abs/2509.15195 |