Foundational Analysis of Safety Engineering Requirements (SAFER)

2026-01-09

arXiv.org

AI Summary

This work addresses the challenges posed by inconsistent, redundant, or missing safety requirements introduced by multiple stakeholders in safety-critical systems, which can lead to significant safety hazards and compliance risks. To tackle this issue, the paper proposes a novel approach that integrates generative artificial intelligence with model-driven engineering. By leveraging formalized requirement specification models to guide AI-based queries, the method enables automated mapping between stakeholder requirements and system functionalities, while efficiently identifying redundancies, conflicts, and omissions. This represents the first systematic integration of generative AI into model-based safety requirements engineering, substantially enhancing the rigor and reliability of early-stage safety architectures. Evaluation on an autonomous unmanned aerial vehicle system demonstrates a marked improvement in detecting requirement inconsistencies, validating the approach’s effectiveness in improving both the efficiency and trustworthiness of safety engineering practices.

Technology Category

• Philosophy and Ethics of AI: Safety, Robustness & Trustworthiness
• Constraint Satisfaction and Optimization: Satisfiability Modulo Theories
• Planning, Routing, and Scheduling: Model-Based Reasoning

Application Category

• Search and Retrieval-Augmented AI: Web evaluation methodologies and metrics
• Social Networks and Social Media: Generative AI / large language models and their impact on social systems
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications

Abstract

We introduce a framework for Foundational Analysis of Safety Engineering Requirements (SAFER), a model-driven methodology supported by Generative AI to improve the generation and analysis of safety requirements for complex safety-critical systems. Safety requirements are often specified by multiple stakeholders with uncoordinated objectives, leading to gaps, duplications, and contradictions that jeopardize system safety and compliance. Existing approaches are largely informal and insufficient for addressing these challenges. SAFER enhances Model-Based Systems Engineering (MBSE) by consuming requirement specification models and generating the following results: (1) mapping requirements to system functions, (2) identifying functions with insufficient requirement specifications, (3) detecting duplicate requirements, and (4) identifying contradictions within requirement sets. SAFER provides structured analysis, reporting, and decision support for safety engineers. We demonstrate SAFER on an autonomous drone system, significantly improving the detection of requirement inconsistencies, enhancing both efficiency and reliability of the safety engineering process. We show that Generative AI must be augmented by formal models and queried systematically, to provide meaningful early-stage safety requirement specifications and robust safety architectures.

Problem

• safety requirements
• stakeholder coordination
• requirement inconsistencies
• safety-critical systems
• compliance

Innovation

• Generative AI
• Model-Based Systems Engineering
• Safety Requirements Analysis
• Requirement Contradiction Detection
• Safety-Critical Systems