# An Intrusion Detection System based on Deep Belief Networks

arXiv: https://arxiv.org/abs/2207.02117 · HTML: https://mlsanity.com/paper/2207.02117/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 3 of its 32 references that are in the map.
- First posted on arXiv 5 Jul 2022.

## Builds on (most cited first, 3 of 3)

- [Realtime Robust Malicious Traffic Detection via Frequency Domain Analysis](https://mlsanity.com/paper/2106.14707/) (2021)
- [Early Stage Malware Prediction Using Recurrent Neural Networks](https://mlsanity.com/paper/1708.03513/) (2017)
- [LUCID: A Practical, Lightweight Deep Learning Solution for DDoS Attack Detection](https://mlsanity.com/paper/2002.04902/) (2020)

## Built on by (most cited first, 4 of 4)

- [Creating an Explainable Intrusion Detection System Using Self Organizing Maps](https://mlsanity.com/paper/2207.07465/) (2022)
- [Federated Deep Learning for Intrusion Detection in IoT Networks](https://mlsanity.com/paper/2306.02715/) (2023)
- [Expectations Versus Reality: Evaluating Intrusion Detection Systems in Practice](https://mlsanity.com/paper/2403.17458/) (2024)
- [MAWIFlow Benchmark: Realistic Flow-Based Evaluation for Network Intrusion Detection](https://mlsanity.com/paper/2506.17041/) (2025)

## Abstract (arXiv)

The rapid growth of connected devices has led to the proliferation of novel cyber-security threats known as zero-day attacks. Traditional behaviour-based IDS rely on DNN to detect these attacks. The quality of the dataset used to train the DNN plays a critical role in the detection performance, with underrepresented samples causing poor performances. In this paper, we develop and evaluate the performance of DBN on detecting cyber-attacks within a network of connected devices. The CICIDS2017 dataset was used to train and evaluate the performance of our proposed DBN approach. Several class balancing techniques were applied and evaluated. Lastly, we compare our approach against a conventional MLP model and the existing state-of-the-art. Our proposed DBN approach shows competitive and promising results, with significant performance improvement on the detection of attacks underrepresented in the training dataset.