{"ID":2850261,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2510.22224","arxiv_id":"2510.22224","title":"Taming Silent Failures: A Framework for Verifiable AI Reliability","abstract":"The integration of Artificial Intelligence (AI) into safety-critical systems introduces a new reliability paradigm: silent failures, where AI produces confident but incorrect outputs that can be dangerous. This paper introduces the Formal Assurance and Monitoring Environment (FAME), a novel framework that confronts this challenge. FAME synergizes the mathematical rigor of offline formal synthesis with the vigilance of online runtime monitoring to create a verifiable safety net around opaque AI components. We demonstrate its efficacy in an autonomous vehicle perception system, where FAME successfully detected 93.5% of critical safety violations that were otherwise silent. By contextualizing our framework within the ISO 26262 and ISO/PAS 8800 standards, we provide reliability engineers with a practical, certifiable pathway for deploying trustworthy AI. FAME represents a crucial shift from accepting probabilistic performance to enforcing provable safety in next-generation systems.","short_abstract":"The integration of Artificial Intelligence (AI) into safety-critical systems introduces a new reliability paradigm: silent failures, where AI produces confident but incorrect outputs that can be dangerous. This paper introduces the Formal Assurance and Monitoring Environment (FAME), a novel framework that confronts thi...","url_abs":"https://arxiv.org/abs/2510.22224","url_pdf":"https://arxiv.org/pdf/2510.22224v1","authors":"[\"Guan-Yan Yang\",\"Farn Wang\"]","published":"2025-10-25T09:07:47Z","proceeding":"cs.SE","tasks":"[\"cs.SE\",\"cs.AI\",\"cs.LG\",\"cs.LO\",\"eess.SY\"]","methods":"[]","has_code":false}