Enhancing Autonomous Online Intrusion Detection for IoT with Balanced Learning, Reliable Pseudo-Labels, and Lightweight Architectures
Fuente:
arXiv
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866917532975235072 |
|---|---|
| author | Afzaal, Hanzala Memon, Danish Raza, Chouhdary Bilal Shahzad, Muhammad Khurram |
| author_facet | Afzaal, Hanzala Memon, Danish Raza, Chouhdary Bilal Shahzad, Muhammad Khurram |
| contents | The rapid proliferation of Internet of Things (IoT) devices has created an urgent demand for adaptive, resource-efficient Intrusion Detection Systems (IDS) capable of handling dynamic and evolving cyber threats. This paper investigates AOC-IDS, a state-of-the-art autonomous online IDS published at IEEE INFOCOM 2024, which employs an Autoencoder (AE) with Cluster Repelling Contrastive (CRC) loss and an autonomous Gaussian-based decision module. We first successfully replicate AOC-IDS on the UNSW-NB15 benchmark, achieving 89.39% accuracy in close agreement with the published 89.19%. We then identify four key limitations: class imbalance, unreliable pseudo-label generation, limited generalization, and computational overhead for IoT deployment, and propose targeted improvements for each. Our XGBoost-BalSamp method achieves 95.45% accuracy on UNSW-NB15, a gain of 6.26% over the baseline. Our combined deep learning approach (PseudoFilter, MixupAug, and LiteAE) achieves a best-run accuracy of 90.88% (F1: 91.45%), surpassing the base paper while reducing model parameters by 55%.These results demonstrate that targeted improvements to AOC-IDS yield consistent accuracy gains while improving practical deployability on IoT edge devices. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2605_26166 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Enhancing Autonomous Online Intrusion Detection for IoT with Balanced Learning, Reliable Pseudo-Labels, and Lightweight Architectures Afzaal, Hanzala Memon, Danish Raza, Chouhdary Bilal Shahzad, Muhammad Khurram Cryptography and Security Artificial Intelligence Machine Learning The rapid proliferation of Internet of Things (IoT) devices has created an urgent demand for adaptive, resource-efficient Intrusion Detection Systems (IDS) capable of handling dynamic and evolving cyber threats. This paper investigates AOC-IDS, a state-of-the-art autonomous online IDS published at IEEE INFOCOM 2024, which employs an Autoencoder (AE) with Cluster Repelling Contrastive (CRC) loss and an autonomous Gaussian-based decision module. We first successfully replicate AOC-IDS on the UNSW-NB15 benchmark, achieving 89.39% accuracy in close agreement with the published 89.19%. We then identify four key limitations: class imbalance, unreliable pseudo-label generation, limited generalization, and computational overhead for IoT deployment, and propose targeted improvements for each. Our XGBoost-BalSamp method achieves 95.45% accuracy on UNSW-NB15, a gain of 6.26% over the baseline. Our combined deep learning approach (PseudoFilter, MixupAug, and LiteAE) achieves a best-run accuracy of 90.88% (F1: 91.45%), surpassing the base paper while reducing model parameters by 55%.These results demonstrate that targeted improvements to AOC-IDS yield consistent accuracy gains while improving practical deployability on IoT edge devices. |
| title | Enhancing Autonomous Online Intrusion Detection for IoT with Balanced Learning, Reliable Pseudo-Labels, and Lightweight Architectures |
| topic | Cryptography and Security Artificial Intelligence Machine Learning |
| url | https://arxiv.org/abs/2605.26166 |