cid 4351220aac29ed3185b2122ed32b0d7912bed4d74aa94e90a16e114c7f6d1897 · original · open access · via openalex
Title: Hayula Research Paper Authors: Hayula AI Lab Venue: Zenodo (CERN European Organization for Nuclear Research) Year: 2026 Canonical: doi:10.5281/zenodo.21274472 URL: https://doi.org/10.5281/zenodo.21274472 Collector: openalex OA: true ABSTRACT ## Abstract h2 Automated vulnerability discovery has long been plagued by high false-positive rates, prohibitive cloud API costs, and the fundamental hallucination problem inherent in language model outputs. The recently proposed Revelio framework (arXiv:2606.22263) addresses these limitations through an agentic architecture that generates executable Proofs-of-Vulnerability (PoVs) verified by sanitizers such as AddressSanitizer and UndefinedBehaviorSanitizer, achieving 19 real vulnerabilities across 7 production projects for approximately \$300 total. In this paper, we present SAIF-Revelio, Hayula Labs' adaptation and extension of Revelio integrated with our existing Security AI Framework (SAIF). SAIF-Revelio deploys eight fine-tuned Qwen2.5-7B specialist models—router, webapp, vulndisc, browser, reveng, network, exploit, and kernel—running entirely on a single Apple M2 Ultra with 192 GB of unified memory. Our system operates 100% locally with zero cloud API calls, ensuring complete data sovereig --- Published on HuggingFace: https://huggingface.co/hayulalab/saif-revelio-paper Website: https://research.hayula.xyz/papers/saif/revelio.html