# Medoid Prototype Alignment for Cross-Plant Unknown Attack Detection in Industrial Control Systems

arXiv: https://arxiv.org/abs/2604.25544 · HTML: https://mlsanity.com/paper/2604.25544/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 22 of its 40 references that are in the map.
- First posted on arXiv 28 Apr 2026.

## Builds on (most cited first, 22 of 22)

- [Domain-Adversarial Training of Neural Networks](https://mlsanity.com/paper/1505.07818/) (2015)
- [Unsupervised Deep Probabilistic Approach for Partial Point Cloud Registration](https://mlsanity.com/paper/2303.13290/) (2023)
- [Deep transfer learning for intrusion detection in industrial control networks: A comprehensive review](https://mlsanity.com/paper/2304.10550/) (2023)
- [An LLM Agent for Automatic Geospatial Data Analysis](https://mlsanity.com/paper/2410.18792/) (2024)
- [Bringing Masked Autoencoders Explicit Contrastive Properties for Point Cloud Self-Supervised Learning](https://mlsanity.com/paper/2407.05862/) (2024)
- [T2TD: Text-3D Generation Model based on Prior Knowledge Guidance](https://mlsanity.com/paper/2305.15753/) (2023)
- [Machine Learning for Intrusion Detection in Industrial Control Systems: Applications, Challenges, and Recommendations](https://mlsanity.com/paper/2202.11917/) (2022)
- [UVMap-ID: A Controllable and Personalized UV Map Generative Model](https://mlsanity.com/paper/2404.14568/) (2024)
- [ZeroReg: Zero-Shot Point Cloud Registration with Foundation Models](https://mlsanity.com/paper/2312.03032/) (2023)
- [Structure Causal Models and LLMs Integration in Medical Visual Question Answering](https://mlsanity.com/paper/2505.02703/) (2025)
- [FreeInsert: Disentangled Text-Guided Object Insertion in 3D Gaussian Scene without Spatial Priors](https://mlsanity.com/paper/2505.01322/) (2025)
- [3D Shape Knowledge Graph for Cross-domain 3D Shape Retrieval](https://mlsanity.com/paper/2210.15136/) (2022)
- [Rethinking the Learning Paradigm for Facial Expression Recognition](https://mlsanity.com/paper/2209.15402/) (2022)
- [Turn Fake into Real: Adversarial Head Turn Attacks Against Deepfake Detection](https://mlsanity.com/paper/2309.01104/) (2023)
- [Large Language Models for Multimodal Deformable Image Registration](https://mlsanity.com/paper/2408.10703/) (2024)
- [Fully-Geometric Cross-Attention for Point Cloud Registration](https://mlsanity.com/paper/2502.08285/) (2025)
- [Organ-Agents: Virtual Human Physiology Simulator via LLMs](https://mlsanity.com/paper/2508.14357/) (2025)
- [Point Cloud Completion Guided by Prior Knowledge via Causal Inference](https://mlsanity.com/paper/2305.17770/) (2023)
- [POCI-Diff: 3D-Layout Guided Diffusion for Controllable Synthetic Surveillance Data Generation](https://mlsanity.com/paper/2601.14056/) (2026)
- [RFR-WWANet: Weighted Window Attention-Based Recovery Feature Resolution Network for Unsupervised Image Registration](https://mlsanity.com/paper/2305.04236/) (2023)
- [Finetune Like You Pretrain: Boosting Zero-shot Adversarial Robustness in Vision-language Models](https://mlsanity.com/paper/2604.11576/) (2026)
- [PoInit-of-View: Poisoning Initialization of Views Transfers Across Multiple 3D Reconstruction Systems](https://mlsanity.com/paper/2604.16540/) (2026)

## Abstract (arXiv)

Deploying an intrusion detector trained in one industrial plant to another remains difficult because Industrial Control System (ICS) traffic is highly site-dependent, labels are scarce, and unseen attacks often appear after deployment. To address this challenge, this paper introduces a medoid prototype alignment framework for cross-plant unknown attack detection. Instead of aligning all source and target samples directly, the method first compresses heterogeneous traffic into a comparable representation space and then extracts robust medoid prototypes that summarize local operational structure in each domain. A prototype-calibrated transfer objective is further designed to align target prototypes with source prototypes while preserving source-domain discrimination and encouraging confident target predictions. This strategy reduces noisy cross-domain matching and improves transfer stability under heterogeneous industrial conditions. Experiments conducted on natural gas and water storage control systems show that the proposed method achieves the best average performance among all compared models, reaching an average accuracy of 0.843 and an average F1-score of 0.838 across four unknown-attack transfer tasks. The analysis also shows clear transfer asymmetry between source-target directions and confirms that prototype guidance is especially helpful on challenging reverse-transfer settings. These findings suggest that medoid prototype alignment is a practical solution for robust industrial intrusion detection under domain shift.