mlsanityData to 14 Oct 2026

Optimized detection of cyber-attacks on IoT networks via hybrid deep learning models

arXiv 2502.11470 ↗First posted 17 Feb 2025cs.CR cs.AIcited by 1

Not on the map. Why?

Abstract (arXiv)

The rapid expansion of Internet of Things (IoT) devices has increased the risk of cyber-attacks, making effective detection essential for securing IoT networks. This work introduces a novel approach combining Self-Organizing Maps (SOMs), Deep Belief Networks (DBNs), and Autoencoders to detect known and previously unseen attack patterns. A comprehensive evaluation using simulated and real-world traffic data is conducted, with models optimized via Particle Swarm Optimization (PSO). The system achieves an accuracy of up to 99.99% and Matthews Correlation Coefficient (MCC) values exceeding 99.50%. Experiments on NSL-KDD, UNSW-NB15, and CICIoT2023 confirm the model's strong performance across diverse attack types. These findings suggest that the proposed method enhances IoT security by identifying emerging threats and adapting to evolving attack strategies.

Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Builds on 10 of its 97 references that are in the map. First posted on arXiv 17 Feb 2025.

Builds on

10 of 97 references.

References · 10

  1. 2023FlowTransformer: A Transformer Framework for Flow-based Network Intrusion Detection Systemscited by 24
  2. 2021HeterPS: Distributed Deep Learning With Reinforcement Learning Based Scheduling in Heterogeneous Environmentscited by 15
  3. 2024Exploration of Attention Mechanism-Enhanced Deep Learning Models in the Mining of Medical Textual Datacited by 11
  4. 2024Enhancing IoT Security with CNN and LSTM-Based Intrusion Detection Systemscited by 9
  5. 2024A Survey of Malware Detection Using Deep Learningcited by 9
  6. 2022IGRF-RFE: A Hybrid Feature Selection Method for MLP-based Network Intrusion Detection on UNSW-NB15 Datasetcited by 7
  7. 2024CNN-LSTM and Transfer Learning Models for Malware Classification based on Opcodes and API Callscited by 5
  8. 2024Deep Multi-Task Learning for Malware Image Classificationcited by 3
  9. 2024Efficient Intrusion Detection: Combining chi2 Feature Selection with CNN-BiLSTM on the UNSW-NB15 Datasetcited by 2
  10. 2024Diagnosing Unknown Attacks in Smart Homes Using Abductive Reasoningcited by 1

Built on by

Cited by year

Citing papers per year: 2025: 1.

1 paper.

  1. 2025A Novel Active Learning Approach to Label One Million Unknown Malware Variantscited by 0