Taming Silent Failures: A Framework for Verifiable AI Reliability

Guan-Yan Yang, Farn Wang
10/25/2025
cs.SEcs.AIcs.LG

No confident code implementation found for this paper. 1 possible match can be shown below.

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.

View on arXivView PDF

Code Implementations

No confident code match yet

We couldn't find an author-owned or strongly-evidenced community implementation for this paper. 1 weaker match is hidden by default — verify before relying on them.

No code implementations found yet.

Know of an implementation? Let us know in the comments below!

Similar Papers

AI Maintenance: A Robustness Perspective

85% match2023

Safe and Certifiable AI Systems: Concepts, Challenges, and Lessons Learned

85% match2025

Landscape of AI safety concerns -- A methodology to support safety assurance for AI-based autonomous systems

84% match2024

Safetywashing: Do AI Safety Benchmarks Actually Measure Safety Progress?

83% match1 repo112024

Towards Responsible AI: Advances in Safety, Fairness, and Accountability of Autonomous Systems

82% match2025

Evaluation and Incident Prevention in an Enterprise AI Assistant

82% match2025

Cite this paper

@article{yang2025taming,
  title  = {Taming Silent Failures: A Framework for Verifiable AI Reliability},
  author = {Guan-Yan Yang and Farn Wang},
  year   = {2025},
  eprint = {2510.22224},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2510.22224v1}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2510.22224.svg)](https://codeofpaper.com/paper/2510.22224)

Discussion