Research

Paper

TESTING February 20, 2026

Generating adversarial inputs for a graph neural network model of AC power flow

Authors

Robert Parker

Abstract

This work formulates and solves optimization problems to generate input points that yield high errors between a neural network's predicted AC power flow solution and solutions to the AC power flow equations. We demonstrate this capability on an instance of the CANOS-PF graph neural network model, as implemented by the PF$Δ$ benchmark library, operating on a 14-bus test grid. Generated adversarial points yield errors as large as 3.4 per-unit in reactive power and 0.08 per-unit in voltage magnitude. When minimizing the perturbation from a training point necessary to satisfy adversarial constraints, we find that the constraints can be met with as little as an 0.04 per-unit perturbation in voltage magnitude on a single bus. This work motivates the development of rigorous verification and robust training methods for neural network surrogate models of AC power flow.

Metadata

arXiv ID: 2602.17975
Provider: ARXIV
Primary Category: cs.LG
Published: 2026-02-20
Fetched: 2026-02-23 05:33

Related papers

Raw Data (Debug)
{
  "raw_xml": "<entry>\n    <id>http://arxiv.org/abs/2602.17975v1</id>\n    <title>Generating adversarial inputs for a graph neural network model of AC power flow</title>\n    <updated>2026-02-20T04:09:13Z</updated>\n    <link href='https://arxiv.org/abs/2602.17975v1' rel='alternate' type='text/html'/>\n    <link href='https://arxiv.org/pdf/2602.17975v1' rel='related' title='pdf' type='application/pdf'/>\n    <summary>This work formulates and solves optimization problems to generate input points that yield high errors between a neural network's predicted AC power flow solution and solutions to the AC power flow equations. We demonstrate this capability on an instance of the CANOS-PF graph neural network model, as implemented by the PF$Δ$ benchmark library, operating on a 14-bus test grid. Generated adversarial points yield errors as large as 3.4 per-unit in reactive power and 0.08 per-unit in voltage magnitude. When minimizing the perturbation from a training point necessary to satisfy adversarial constraints, we find that the constraints can be met with as little as an 0.04 per-unit perturbation in voltage magnitude on a single bus. This work motivates the development of rigorous verification and robust training methods for neural network surrogate models of AC power flow.</summary>\n    <category scheme='http://arxiv.org/schemas/atom' term='cs.LG'/>\n    <category scheme='http://arxiv.org/schemas/atom' term='eess.SY'/>\n    <published>2026-02-20T04:09:13Z</published>\n    <arxiv:primary_category term='cs.LG'/>\n    <author>\n      <name>Robert Parker</name>\n    </author>\n  </entry>"
}