# Diffusion-Based Stress Testing of Overload Monitoring for Resilient Emergency Cellular Networks Using Internet CDR Proxies

arXiv: https://arxiv.org/abs/2610.04526 · HTML: https://mlsanity.com/paper/2610.04526/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 11 of its 23 references that are in the map.
- First posted on arXiv 3 Oct 2026.

## Builds on (most cited first, 11 of 11)

- [Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2006.11239/) (2020)
- [On Calibration of Modern Neural Networks](https://mlsanity.com/paper/1706.04599/) (2017)
- [Diffusion Models for Adversarial Purification](https://mlsanity.com/paper/2205.07460/) (2022)
- [TabDDPM: Modelling Tabular Data with Diffusion Models](https://mlsanity.com/paper/2209.15421/) (2022)
- [Dos and Don'ts of Machine Learning in Computer Security](https://mlsanity.com/paper/2010.09470/) (2020)
- [Artificial General Intelligence (AGI)-Native Wireless Systems: A Journey Beyond 6G](https://mlsanity.com/paper/2405.02336/) (2024)
- [Semantic Successive Refinement: A Generative AI-aided Semantic Communication Framework](https://mlsanity.com/paper/2408.05112/) (2024)
- [Call Detail Records Driven Anomaly Detection and Traffic Prediction in Mobile Cellular Networks](https://mlsanity.com/paper/1807.11545/) (2018)
- [RRC Signaling Storm Detection in O-RAN](https://mlsanity.com/paper/2504.15738/) (2025)
- [MA-HEAD-Net: Adaptive Rule-Guided Multi-Agent DRL for AoI Minimization in UAV-Assisted Emergency Networks](https://mlsanity.com/paper/2608.01128/) (2026)
- [Diff-DDoS: Realistic Cyber-Physical Attack Synthesis and Robust Detection for 5G-Enabled CPS Using Tabular Diffusion Models](https://mlsanity.com/paper/2608.17796/) (2026)

## Abstract (arXiv)

Disasters can overload cellular control-plane signaling within minutes, yet fine-grained Radio Resource Control (RRC) or Next Generation (NG) Application Protocol (NGAP) telemetry is privacy-sensitive and costly to collect for analytics. Many emergency monitoring pipelines therefore rely on coarse Call Detail Record (CDR) aggregates. We treat Internet activity in CDR grids as a practical proxy for hidden signaling stress under that constraint. We train a lightweight convolutional neural network (CNN) on stylized overload injections, stress-test it with diffusion-synthesized surges that preserve normal traffic structure, and adapt the detector by retraining on hard synthetic samples. Under stress-test conditions, the default alert threshold fails even though receiver operating characteristic (ROC) curves stay strong: the detector still assigns overloaded cells a larger overload probability than normal cells, but those probabilities fall below the default cutoff 0.5 and are labeled normal, so the F1-maximizing threshold -- selected post hoc on the same stress-test grids (oracle τ^*) -- shifts by 0.32 ± 0.03 (operating-point drift). Across three random seeds, hard-sample adaptation raises thresholded performance (F1) from 0% (no alerts at the default cutoff 0.5 on any seed) to 85.67 ± 14.37% and ranking from ROC-AUC 0.886 ± 0.040 to 0.99996 ± 0.00007. Diffusion-synthesized surges expose threshold fragility that matched-condition training -- training and testing on the same stylized injections -- hides, and hard-sample adaptation restores usable alerts at the default cutoff. Together, these steps define a reusable pre-deployment stress test for emergency monitors. Internet-only CDR input further supports lightweight AI-native workflows that combine monitoring, recalibration, and adaptation.