# Robust Industrial Cyber Physical Classification Using Neuromorphic Temporal Embeddings and Hybrid SNN XGBoost Under Machine Unlearning Attacks

arXiv: https://arxiv.org/abs/2609.09564 · HTML: https://mlsanity.com/paper/2609.09564/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Backdoor and data poisoning attacks, one of 12 directions in LLM safety and security.
- Builds on 18 of its 42 references that are in the map.
- First posted on arXiv 9 Sep 2026.

## Placed in

- LLM safety and security / [Backdoor and data poisoning attacks](https://mlsanity.com/safety/backdoor-and-data-poisoning-attacks/)

## Builds on (most cited first, 18 of 18)

- [Certified Adversarial Robustness via Randomized Smoothing](https://mlsanity.com/paper/1902.02918/) (2019)
- [BadNets: Identifying Vulnerabilities in the Machine Learning Model Supply Chain](https://mlsanity.com/paper/1708.06733/) (2017)
- [Machine Unlearning](https://mlsanity.com/paper/1912.03817/) (2019)
- [Surrogate Gradient Learning in Spiking Neural Networks](https://mlsanity.com/paper/1901.09948/) (2019)
- [Training Spiking Neural Networks Using Lessons From Deep Learning](https://mlsanity.com/paper/2109.12894/) (2021)
- [Neural Oblivious Decision Ensembles for Deep Learning on Tabular Data](https://mlsanity.com/paper/1909.06312/) (2019)
- [Machine Unlearning: Solutions and Challenges](https://mlsanity.com/paper/2308.07061/) (2023)
- [Modeling Realistic Adversarial Attacks against Network Intrusion Detection Systems](https://mlsanity.com/paper/2106.09380/) (2021)
- [Graph Neural Networks Based Detection of Stealth False Data Injection Attacks in Smart Grids](https://mlsanity.com/paper/2104.02012/) (2021)
- [Joint Detection and Localization of Stealth False Data Injection Attacks in Smart Grids using Graph Neural Networks](https://mlsanity.com/paper/2104.11846/) (2021)
- [Dynamic Detection of False Data Injection Attack in Smart Grid using Deep Learning](https://mlsanity.com/paper/1808.01094/) (2018)
- [Cyberattack Detection in Large-Scale Smart Grids using Chebyshev Graph Convolutional Networks](https://mlsanity.com/paper/2112.13166/) (2021)
- [A Temporal Graph Neural Network for Cyber Attack Detection and Localization in Smart Grids](https://mlsanity.com/paper/2212.03390/) (2022)
- [Spiking Neural Networks with Single-Spike Temporal-Coded Neurons for Network Intrusion Detection](https://mlsanity.com/paper/2010.07803/) (2020)
- [Neuromorphic Cybersecurity with Semi-supervised Lifelong Learning](https://mlsanity.com/paper/2508.04610/) (2025)
- [Explainable Autoencoder-Based Anomaly Detection in IEC 61850 GOOSE Networks](https://mlsanity.com/paper/2601.09287/) (2026)
- [PowerFDNet: Deep Learning-Based Stealthy False Data Injection Attack Detection for AC-model Transmission Systems](https://mlsanity.com/paper/2207.10805/) (2022)
- [Evaluation of Real-Time Mitigation Techniques for Cyber Security in IEC 61850 / IEC 62351 Substations](https://mlsanity.com/paper/2511.18748/) (2025)

## Abstract (arXiv)

The digitalisation of electrical distribution networks has increased the exposure of power-grid infrastructure to cyber attacks. Existing intrusion detection systems (IDSs), however, often rely on computationally expensive deep learning models that are difficult to deploy at the edge. Periodic retraining also exposes these systems to machine unlearning attacks, where selective data removal can degrade detection performance. We propose a hybrid Spiking Neural Network (SNN) and XGBoost architecture that combines efficient temporal encoding with a lightweight classifier and provides structural resilience to such attacks. The SNN is trained once on clean data and used as a fixed feature extractor, while only the XGBoost classifier is retrained during model updates. Evaluated on two real-world public power-system datasets, the proposed method achieves 99.9% accuracy (F1-macro 0.999) on the Synchrophasor dataset and 95.0% accuracy (F1-macro 0.943) on the MSU/ORNL dataset, outperforming standalone baselines. Under selective label-flipping attacks, the hybrid model loses only 0.9% F1-macro at 10% poisoning and delays target-class collapse from 60% to 70% poisoning compared with raw models. These results demonstrate that neuromorphic temporal encoding can provide both accurate cyber-attack detection and improved resilience to data poisoning in cyber-physical systems.