Fighting AI with AI: Leveraging Foundation Models for Assuring AI-Enabled Safety-Critical Systems

TL;DR

This paper presents a novel approach using large language and vision models to improve the assurance, verification, and validation of AI components in safety-critical systems, addressing key transparency and specification challenges.

Contribution

It introduces REACT and SemaLens, two AI-driven tools that enhance requirements formalization and perception system analysis for safety-critical AI applications.

Findings

REACT enables early verification of natural language requirements.

SemaLens improves testing and monitoring of perception systems.

The combined approach enhances AI safety assurance processes.

Abstract

The integration of AI components, particularly Deep Neural Networks (DNNs), into safety-critical systems such as aerospace and autonomous vehicles presents fundamental challenges for assurance. The opacity of AI systems, combined with the semantic gap between high-level requirements and low-level network representations, creates barriers to traditional verification approaches. These AI-specific challenges are amplified by longstanding issues in Requirements Engineering, including ambiguity in natural language specifications and scalability bottlenecks in formalization. We propose an approach that leverages AI itself to address these challenges through two complementary components. REACT (Requirements Engineering with AI for Consistency and Testing) employs Large Language Models (LLMs) to bridge the gap between informal natural language requirements and formal specifications, enabling early verification and validation. SemaLens (Semantic Analysis of Visual Perception using large Multi-modal models) utilizes Vision Language Models (VLMs) to reason about, test, and monitor DNN-based perception systems using human-understandable concepts. Together, these components provide a comprehensive pipeline from informal requirements to validated implementations.