An intrusion detection model based on Convolutional Kolmogorov-Arnold Networks

Scientific Reports, Journal Year: 2025, Volume and Issue: 15(1)

Published: Jan. 14, 2025

The application of artificial neural networks (ANNs) can be found in numerous fields, including image and speech recognition, natural language processing, autonomous vehicles. As well, intrusion detection, the subject this paper, relies heavily on it. Different detection models have been constructed using ANNs. While ANNs are relatively mature to construct models, some challenges remain. Among most notorious these bloated caused by large number parameters, non-interpretability models. Our paper presents Convolutional Kolmogorov-Arnold Networks (CKANs), which designed overcome difficulties provide an interpretable accurate model. (KANs) developed from representation theorem. Meanwhile, CKAN incorporates a convolutional computational mechanism based KAN. model proposed is incorporating attention mechanisms into CKAN's logic. datasets CICIoT2023 CICIoMT2024 were used for training validation. From results evaluating performance indicators experiments, CKANs has attractive prospect. compared with other methods, predict much higher level accuracy significantly fewer parameters. However, it not superior terms memory usage, execution speed energy consumption.

Language: Английский

---

Research on interpretable graph neural network agent model for siltation diagnosis in Urban-Scale sewer systems

Tunnelling and Underground Space Technology, Journal Year: 2025, Volume and Issue: 162, P. 106666 - 106666

Published: April 16, 2025

Language: Английский

---

A comprehensive systematic review of intrusiondetection systems: emerging techniques,challenges, and future research directions

Journal of Edge Computing, Journal Year: 2025, Volume and Issue: unknown

Published: April 15, 2025

The role of Intrusion Detection Systems (IDS) in the protection against increasing variety cybersecurity threats complex environments, including Internet Things (IoT), cloud computing, and industrial networks. This study evaluates existing state-of-the-art IDS methodologies using Deep Learning (DL) approaches, advanced feature engineering techniques. research also highlights success models such as Genetic Algorithms (GA), Particle Swarm Optimization (PSO), Explainable AI (XAI) improving detection accuracy well computational efficiency interoperability. Blockchain quantum computing technologies are explored to improve data privacy, resilience, scalability decentralized resource-constrained environments. work primarily identifies key challenges, real-time anomaly detection, adversarial robustness, imbalance datasets, assist researchers investigating further opportunities. Focusing on future filling these gaps, proceeds toward developing lightweight, adaptive, ethical frameworks that can operate across dynamic heterogeneous In this paper, opportunities, strategies critically synthesized create a useful resource for academics, researchers, industry practitioners.

Language: Английский

---

SC-MLIDS: Fusion-based Machine Learning framework for intrusion detection in wireless sensor networks

Ad Hoc Networks, Journal Year: 2025, Volume and Issue: unknown, P. 103871 - 103871

Published: April 1, 2025

Language: Английский

---

Enhanced Cyber Security: Sparse Computation-Empowered Multi-class SVM Intrusion Detection

Lecture notes in networks and systems, Journal Year: 2025, Volume and Issue: unknown, P. 435 - 447

Published: Jan. 1, 2025

Language: Английский

---

Towards intrusion detection in fog environments using generative adversarial network and long short-term memory network

Computers & Security, Journal Year: 2024, Volume and Issue: 145, P. 104004 - 104004

Published: July 27, 2024

Language: Английский

---

DDP-DAR: Network Intrusion Detection Based on Denoising Diffusion Probabilistic Model and Dual-Attention Residual Network

Neural Networks, Journal Year: 2024, Volume and Issue: 184, P. 107064 - 107064

Published: Dec. 19, 2024

Language: Английский

---

Optimization of Network Intrusion Detection Model Based on Big Data Analysis

Journal of Cyber Security and Mobility, Journal Year: 2024, Volume and Issue: unknown

Published: Nov. 23, 2024

As user usage grows, so do security threats to networks, the Internet, websites, and organizations. Detecting intrusions in such a big data situation is complex. A feature-optimized network intrusion detection model based on extensive analysis designed overcome limitations of current models obtain more ideal results. Firstly, modeling status studied, influence features results analyzed. Then, feature optimization mathematical established. The solution searched by an adaptive genetic algorithm simulating natural biological evolution. optimal subset obtained back coding solution. Finally, according subset, learning sample modeled, designed. Using standard set for simulation comparison tests, average accuracy this paper’s about 95%, while other are below 95%. Meanwhile, time training significantly reduced, better efficiency can be obtained.

Language: Английский

---

ExBCIL: an exemplar-based class incremental learning for intrusion detection system

International Journal of Machine Learning and Cybernetics, Journal Year: 2024, Volume and Issue: unknown

Published: Dec. 25, 2024

Language: Английский

---