Detection of DDoS attacks in SDN with Siberian Tiger Optimization algorithm and deep learning DOI Creative Commons

Naseer Hameed Saadoon Al-Sarray,

Javad Rahebi, Ayşe Demi̇rhan

et al.

Research Square (Research Square), Journal Year: 2024, Volume and Issue: unknown

Published: March 19, 2024

Abstract The Software-defined Networking (SDN) system plays a crucial role in efficiently overseeing the Internet network by segregating control and data planes. In SDN, controller manages determines policy sending setting SDN switches. Despite significant advantages, has security challenges. DDoS attacks are main challenge networks. primarily target to disrupt performance. Intrusion detection systems networks need confidential methods for message exchange coordination of controllers so that they can blacklist attacking addresses with each other. this manuscript, we introduce an approach utilizing 1D CNN LSTM detecting network, incorporating information hidden images. first stage, game theory deep learning based on GAN used increase attack accuracy balance set. second uses extract primary features, Siberian tiger optimization (STO) algorithm is applied enhance efficiency network. third step, STO selects optimal features. Finally, classifies traffic receiving selected use image encryption privacy exchanging sharing blacklists. tests performed Python datasets UNSW-NB15, CIC-IDS2017, NSL-KDD 99.49%, 99.86%, 99.91%. proposed method GAN-CL-STO demonstrates higher compared CNN-LSTM, HODNN+CRF, CNN, PSO-1D CNN+BiLSTM methods. suggested identifying more accurate than WOA, HHO, COA feature selection

Language: Английский

SoK: quantum computing methods for machine learning optimization DOI
Hamza Baniata

Quantum Machine Intelligence, Journal Year: 2024, Volume and Issue: 6(2)

Published: July 24, 2024

Language: Английский

Citations

4
Deep-Learning-Based Approach for IoT Attack and Malware Detection DOI Creative Commons
Burak Taşçı

Applied Sciences, Journal Year: 2024, Volume and Issue: 14(18), P. 8505 - 8505

Published: Sept. 20, 2024

The Internet of Things (IoT), introduced by Kevin Ashton in the late 1990s, has transformed technology usage globally, enhancing efficiency and convenience but also posing significant security challenges. With proliferation IoT devices expected to exceed 29 billion 2030, securing these is crucial. This study proposes an optimized 1D convolutional neural network (1D CNN) model for effectively classifying data. architecture includes input, convolutional, self-attention, output layers, utilizing GELU activation, dropout, normalization techniques improve performance prevent overfitting. was evaluated using CIC 2023, CIC-MalMem-2022, CIC-IDS2017 datasets, achieving impressive results: 98.36% accuracy, 100% precision, 99.96% recall, 99.95% F1-score 2023; 99.90% 99.98% 99.97% CIC-MalMem-2022; 99.99% CIC-IDS2017. These outcomes demonstrate model’s effectiveness detecting various IoT-related attacks malware. highlights potential deep-learning enhance security, with developed showing high low computational overhead, making it suitable real-time applications resource-constrained devices. Future research should aim at testing on larger datasets incorporating adaptive learning capabilities further its robustness. significantly contributes providing advanced insights into deploying models, encouraging exploration this dynamic field.

Language: Английский

Citations

4
QoS-Aware cloud security using lightweight EfficientNet with Adaptive Sparse Bayesian Optimization DOI

J Vinothini,

Srie Vidhya Janani E

Peer-to-Peer Networking and Applications, Journal Year: 2025, Volume and Issue: 18(2)

Published: Jan. 20, 2025

Language: Английский

Citations

0
A Lidar wind speed measurement system based on SSA-1DCNN algorithm DOI

Anni Ying,

Bing Yin,

Chonggao Hu

et al.

Journal of Modern Optics, Journal Year: 2025, Volume and Issue: unknown, P. 1 - 11

Published: Feb. 4, 2025

Language: Английский

Citations

0
Evolutionary LightGBM‐Based Intrusion Detection System for IoT Networks DOI Open Access

Khushi Singal,

Nisha Kandhoul,

Sanjay K. Dhurander

et al.

International Journal of Communication Systems, Journal Year: 2025, Volume and Issue: 38(5)

Published: Feb. 20, 2025

ABSTRACT With the rapid growth of Internet Things (IoT), securing interconnected devices is becoming increasingly critical. This paper introduces LightShield intrusion detection system (IDS) to enhance in IoT environments using high‐performance computing. features preprocessing data, ReliefF algorithm for feature selection, and a novel model based on LightGBM , gradient boosting framework. The leverages GPU acceleration faster validation, enabling real‐time monitoring. By adapting characteristics, provides flexible, scalable defense against evolving cyber threats. Results show its potential improve security ecosystems, offering valuable insights into anomaly‐based future secure networks. binary classification displayed exceptional precision with 99.82 % accuracy detecting attacks, multiclass achieved commendable 97.25 classifying distinct attack types.

Language: Английский

Citations

0
Online Machine Learning for Intrusion Detection in Electric Vehicle Charging Systems DOI Creative Commons

Fazliddin Makhmudov,

Dusmurod Kilichev, Ulugbek Giyosov

et al.

Mathematics, Journal Year: 2025, Volume and Issue: 13(5), P. 712 - 712

Published: Feb. 22, 2025

Electric vehicle (EV) charging systems are now integral to smart grids, increasing the need for robust and scalable cyberattack detection. This study presents an online intrusion detection system that leverages Adaptive Random Forest classifier with Windowing drift identify real-time evolving threats in EV infrastructures. The is evaluated using real-world network traffic from CICEVSE2024 dataset, ensuring practical applicability. For binary detection, model achieves 0.9913 accuracy, 0.9999 precision, 0.9914 recall, F1-score of 0.9956, demonstrating highly accurate threat It effectively manages concept drift, maintaining average accuracy 0.99 during events. In multiclass attains 0.9840 0.9831 event 0.96. computationally efficient, processing each instance just 0.0037 s, making it well-suited deployment. These results confirm machine learning methods can secure source code publicly available on GitHub, reproducibility fostering further research. provides a efficient cybersecurity solution protecting networks threats.

Language: Английский

Citations

0
NSGTO‐LSTM: Niche‐strategy‐based gorilla troops optimization and long short‐term memory network intrusion detection model DOI Creative Commons

Saritha Anchuri,

Arvind Ganesh,

Prathusha Perugu

et al.

ETRI Journal, Journal Year: 2025, Volume and Issue: unknown

Published: March 17, 2025

Abstract In recent decades, the rapid growth of Internet Things (IoT) has highlighted several network security problems. this study, an efficient intrusion detection (ID) system is implemented by using both machine learning and data mining concepts for detecting patterns. During initial phase, are collected from NSL‐KDD University New South Wales‐Network Based 15 (UNSW‐NB15) datasets. The then normalized/scaled employing a standard scaler technique. Next, informative feature values selected proposed optimization algorithm—that is, Niche‐Strategy‐based Gorilla Troops Optimization (NSGTO) algorithm. Finally, these transferred to Long Short‐Term Memory (LSTM) model classify types attacks on comparison existing ID systems, based NSGTO‐LSTM obtains classification accuracy 99.98% 99.90%

Language: Английский

Citations

0
Enhancing hydrological time series forecasting with a hybrid Bayesian-ConvLSTM model optimized by particle swarm optimization DOI Creative Commons
Hüseyin Çağan Kılınç,

Sina Apak,

Mahmut Esad Ergin

et al.

Acta Geophysica, Journal Year: 2025, Volume and Issue: unknown

Published: March 24, 2025

Language: Английский

Citations

0
Artificial intelligence-based non-invasive bilirubin prediction for neonatal jaundice using 1D convolutional neural network DOI Creative Commons
Fatemeh Makhloughi

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

Published: April 4, 2025

Language: Английский

Citations

0
U-shaped deep learning networks for algal bloom detection using Sentinel-2 imagery: Exploring model performance and transferability DOI
İsmail Çölkesen, Mustafacan Saygı, Muhammed Yusuf Öztürk

et al.

Journal of Environmental Management, Journal Year: 2025, Volume and Issue: 381, P. 125152 - 125152

Published: April 5, 2025

Language: Английский

Citations

0