Scale-Aware Adversarial Analysis: A Diagnostic for Generative AI in Multiscale Complex Systems

TL;DR

This paper introduces a scale-aware diagnostic framework using diffusion-based data decomposition to evaluate and improve generative AI models' adherence to physical laws in multiscale systems.

Contribution

It presents a novel CDD-based method for physically constrained data generation and model evaluation, revealing limitations of current generative models in multiscale physics.

Findings

Unconstrained models show localized structural freezing under physical perturbations.

Models fail to maintain cross-scale continuity, diverging in unseen states.

The framework enables controlled testing of model vulnerabilities in physically coherent states.

Abstract

Complex physical systems, from supersonic turbulence to the macroscopic structure of the universe, are governed by continuous multiscale dynamics. While modern machine learning architectures excel at mapping the high-dimensional observables of these systems, it remains unclear whether they internalize the governing physical laws or merely interpolate discrete statistical correlations. Standard Explainable AI (XAI) architectures, particularly perturbation-based and gradient-saliency methods, rely on pixel-wise perturbations, which generate unphysical artifacts and push inputs off the valid empirical distribution. To resolve this, we introduce a diagnostic framework driven by Constrained Diffusion Decomposition (CDD), a diffusion-based multiscale data decomposition algorithm that enables physically constrained data generation and model evaluation via scale-aware modifications. Applying this framework to a Denoising Diffusion Probabilistic Model (DDPM), we execute deterministic interventions directly within the continuous, CDD-based scale space. We demonstrate that under moderate physical perturbations, the unconstrained generative model exhibits localized structural freezing and non-linear instability rather than continuous PDE-like responses. The network fails to maintain cross-scale continuity, causing the generative trajectory to diverge when pushed into unseen physical states. By synthesizing a continuum of physically coherent states, this scale-informed methodology establishes a controlled test ground to evaluate algorithmic vulnerabilities, providing the rigorous physical constraints necessary for future architectures to respect the multiscale causality of the natural universe.