Negative Selection Approach to support Formal Verification and Validation of BlackBox Models' Input Constraints

TL;DR

This paper introduces a Negative Selection Algorithm (NSA) that efficiently identifies unsafe input regions in black-box models for formal verification, leveraging meta-heuristics and parallel processing to improve safety validation.

Contribution

The paper presents a novel NSA-based meta-heuristic method for estimating unsafe input regions in black-box models, enhancing verification processes.

Findings

High precision in identifying unsafe sub-requirements

Effective estimation of large unsafe regions

Validation with Marabou framework confirms results

Abstract

Generating unsafe sub-requirements from a partitioned input space to support verification-guided test cases for formal verification of black-box models is a challenging problem for researchers. The size of the search space makes exhaustive search computationally impractical. This paper investigates a meta-heuristic approach to search for unsafe candidate sub-requirements in partitioned input space. We present a Negative Selection Algorithm (NSA) for identifying the candidates' unsafe regions within given safety properties. The Meta-heuristic capability of the NSA algorithm made it possible to estimate vast unsafe regions while validating a subset of these regions. We utilize a parallel execution of partitioned input space to produce safe areas. The NSA based on the prior knowledge of the safe regions is used to identify candidate unsafe region areas and the Marabou framework is then used to validate the NSA results. Our preliminary experimentation and evaluation show that the procedure finds candidate unsafe sub-requirements when validated with the Marabou framework with high precision.