# Cross-Domain Generalization Failure in Lightweight Intrusion Detection Models for IIoT Networks

arXiv: https://arxiv.org/abs/2607.00553 · HTML: https://mlsanity.com/paper/2607.00553/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 10 of its 30 references that are in the map.
- First posted on arXiv 1 Jul 2026.

## Builds on (most cited first, 10 of 10)

- [A Unified Approach to Interpreting Model Predictions](https://mlsanity.com/paper/1705.07874/) (2017)
- [HopSkipJumpAttack: A Query-Efficient Decision-Based Attack](https://mlsanity.com/paper/1904.02144/) (2019)
- [Adversarial Robustness Toolbox v1.0.0](https://mlsanity.com/paper/1807.01069/) (2018)
- [Deep transfer learning for intrusion detection in industrial control networks: A comprehensive review](https://mlsanity.com/paper/2304.10550/) (2023)
- [Machine Learning Based Network Vulnerability Analysis of Industrial Internet of Things](https://mlsanity.com/paper/1911.05771/) (2019)
- [Towards Adversarial Realism and Robust Learning for IoT Intrusion Detection and Classification](https://mlsanity.com/paper/2301.13122/) (2023)
- [The Cross-evaluation of Machine Learning-based Network Intrusion Detection Systems](https://mlsanity.com/paper/2203.04686/) (2022)
- [On the Cross-Dataset Generalization of Machine Learning for Network Intrusion Detection](https://mlsanity.com/paper/2402.10974/) (2024)
- [Review on the Feasibility of Adversarial Evasion Attacks and Defenses for Network Intrusion Detection Systems](https://mlsanity.com/paper/2303.07003/) (2023)
- [Gotham Dataset 2025: A Reproducible Large-Scale IoT Network Dataset for Intrusion Detection and Security Research](https://mlsanity.com/paper/2502.03134/) (2025)

## Built on by (most cited first, 2 of 2)

- [Provenance, Not Behaviour: A Serialisation Artifact in Edge-IIoTset and a Leakage-Free Benchmark for Precision-Agriculture Intrusion Detection](https://mlsanity.com/paper/2608.15761/) (2026)
- [A Three-Axis Stress Test of LLM vs Classical ML for Network Intrusion Detection under Distribution Shift and Adversarial Evasion](https://mlsanity.com/paper/2609.13511/) (2026)

## Abstract (arXiv)

Lightweight machine learning models are increasingly proposed for intrusion detection in Industrial Internet of Things (IIoT) networks due to their suitability for resource-constrained edge deployment. Most reported results evaluate these models only within their training network, leaving behavior on unseen networks unverified. This study trains four lightweight architectures on one IIoT dataset and evaluates them, without retraining, on two structurally distinct IIoT datasets using a feature representation restricted to attributes available across all three sources. Explainability analysis across two top-performing models shows both rely overwhelmingly on coarse port-category features; the most influential category occurs in source-domain attack traffic at 96 to 435 times the rate in the two target domains, indicating that coarsening port resolution relocates rather than removes a documented shortcut. Evaluation under naturally imbalanced class distributions reveals a further effect: the evaluation protocol used can reverse which target network appears to pose the greater generalization challenge. Adversarial robustness and recovery through limited target-domain exposure are also assessed; robustness to adversarial perturbation is unrelated to cross-network generalization, and recovery through adaptation varies considerably by architecture. These findings suggest deployment readiness should be assessed using cross-network evaluation under realistic class distributions, rather than within-domain accuracy alone.