Formal Verification for Deep Learning-based Power Control in Massive MIMO

2026-07-15

AI Summary

This work addresses the vulnerability of deep learning–based power control in massive MIMO systems to input perturbations—such as user location errors—and the absence of formal robustness guarantees. It presents the first formal verification framework for deep neural networks in regression tasks with nonlinear output constraints, combining DeepPoly abstract bound propagation with constraint programming. Adversarial perturbations are modeled as hyperrectangular sets, and a constrained numerical feasibility problem is formulated to ensure a provable lower bound on performance. Experimental results demonstrate that well-trained models exhibit local robustness under position perturbations of up to ±1 meter, with an optimality gap no greater than 1%.

Abstract

Deep learning is a promising approach to optimize wireless communication by simplifying the search for near-optimal solutions. Prior studies on deep learning-based wireless communication optimization have explored supervised learning approaches that map raw user information, such as location or channel state information, to optimal power allocation vectors. While this approach demonstrates competitive performance, it is susceptible to adversarial attacks via input perturbations. Current defense mechanisms primarily rely on empirical methods, which do not provide formal guarantees of robustness. We fill this gap by proposing a formal verification framework to evaluate the robustness of deep learning-based power allocation in multi-cell massive multiple-input multiple-output (MIMO) systems against a wide range of potential adversarial input manipulations. To the best of our knowledge, this is the first attempt to formally verify deep neural networks in a regression setting with non-linear output constraints. We model the adversary's capabilities using hyper-rectangle constraints on their perturbation, adopt the abstraction-based bound-propagation technique (DeepPoly) to bound the interval of potential allocated powers, and formulate the minimum performance requirements as a constrained program for numerical feasibility analysis. Evaluation on publicly available datasets for power allocation in multi-cell massive MIMO indicates that a well-trained model can guarantee the local robustness under location perturbation by +-1m while retaining a maximum 1% optimality gap.

Problem

• formal verification
• deep learning
• power control
• massive MIMO
• adversarial robustness

Innovation

• formal verification
• deep learning
• massive MIMO
• robustness
• power control