Detecting cyber attacks in vehicle networks using improved LSTM based optimization methodology DOI Creative Commons

C. Jayasri,

V. Balaji,

C. M. Nalayini

и другие.

Scientific Reports, Год журнала: 2025, Номер 15(1)

Опубликована: Май 31, 2025

The growing adoption of intelligent transportation systems and connected vehicle networks has raised significant cybersecurity concerns due to their vulnerability cyberattacks such as spoofing, message tampering, denial-of-service. Traditional intrusion detection struggle cope with the dynamic high-volume nature vehicular data, often leading high false positives limited adaptability. To address this problem, study proposes an enhanced deep learning-based optimization framework for detecting in networks. methodology employs UNSW-NB15 dataset, data preprocessed using Maximum-Minimum Normalization. Feature extraction is performed Discrete Fourier Transform (DFT), capturing frequency-domain patterns indicative anomalies. Detection executed through Improved Long Short-Term Memory (ILSTM) model, whose parameters are optimized Crocodile Optimization Algorithm (COA), aiming maximize classification accuracy. Experimental results demonstrate that proposed ILSTM-COA model significantly outperforms existing techniques, achieving 98.9% accuracy showing notable improvements across sensitivity, specificity, other performance metrics. This offers a robust, scalable, real-time solution safeguarding against evolving cyber threats.

Язык: Английский

Improved network anomaly detection system using optimized autoencoder − LSTM DOI

S. Narmadha,

Balaji Narayanan

Expert Systems with Applications, Год журнала: 2025, Номер unknown, С. 126854 - 126854

Опубликована: Фев. 1, 2025

Язык: Английский

Процитировано

2
End-to-end multi-task reinforcement learning-based UAV swarm communication attack detection and area coverage DOI
Jin Yu, Ya Zhang, Changyin Sun

и другие.

Knowledge-Based Systems, Год журнала: 2025, Номер unknown, С. 113390 - 113390

Опубликована: Март 1, 2025

Язык: Английский

Процитировано

0
Detecting cyber attacks in vehicle networks using improved LSTM based optimization methodology DOI Creative Commons

C. Jayasri,

V. Balaji,

C. M. Nalayini

и другие.

Scientific Reports, Год журнала: 2025, Номер 15(1)

Опубликована: Май 31, 2025

The growing adoption of intelligent transportation systems and connected vehicle networks has raised significant cybersecurity concerns due to their vulnerability cyberattacks such as spoofing, message tampering, denial-of-service. Traditional intrusion detection struggle cope with the dynamic high-volume nature vehicular data, often leading high false positives limited adaptability. To address this problem, study proposes an enhanced deep learning-based optimization framework for detecting in networks. methodology employs UNSW-NB15 dataset, data preprocessed using Maximum-Minimum Normalization. Feature extraction is performed Discrete Fourier Transform (DFT), capturing frequency-domain patterns indicative anomalies. Detection executed through Improved Long Short-Term Memory (ILSTM) model, whose parameters are optimized Crocodile Optimization Algorithm (COA), aiming maximize classification accuracy. Experimental results demonstrate that proposed ILSTM-COA model significantly outperforms existing techniques, achieving 98.9% accuracy showing notable improvements across sensitivity, specificity, other performance metrics. This offers a robust, scalable, real-time solution safeguarding against evolving cyber threats.

Язык: Английский

Процитировано

0