A file archival integrity check method based on the BiLSTM + CNN model and deep learning

Egyptian Informatics Journal, Journal Year: 2025, Volume and Issue: 29, P. 100597 - 100597

Published: Jan. 9, 2025

Language: Английский

---

Multi-attention DeepCRNN: an efficient and explainable intrusion detection framework for Internet of Medical Things environments

Knowledge and Information Systems, Journal Year: 2025, Volume and Issue: unknown

Published: April 5, 2025

Language: Английский

---

A two-tier optimization strategy for feature selection in robust adversarial attack mitigation on internet of things network security

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

Published: Jan. 17, 2025

Adversarial attacks were commonly considered in computer vision (CV), but their effect on network security apps rests the field of open investigation. As IoT, AI, and 5G endure to unite understand potential Industry 4.0, events incidents IoT systems have been enlarged. While networks efficiently deliver intellectual services, vast amount data processed collected also creates severe concerns. Numerous research works keen project intelligent intrusion detection (NIDS) avert exploitation through smart applications. Deep learning (DL) models are applied perceive alleviate numerous against networks. DL has a considerable reputation NIDS, owing its robust ability identify delicate differences between malicious normal activities. diversity aimed at influencing techniques for protection, whether these methods exposed adversarial examples is unidentified. This study introduces Two-Tier Optimization Strategy Robust Attack Mitigation (TTOS-RAAM) model security. The major aim TTOS-RAAM technique recognize presence attack behaviour IoT. Primarily, utilizes min-max scaler scale input into uniform format. Besides, hybrid coati-grey wolf optimization (CGWO) approach utilized optimum feature selection. Moreover, employs conditional variational autoencoder (CVAE) detect attacks. Finally, parameter adjustment CVAE performed by utilizing an improved chaos African vulture (ICAVO) model. A wide range experimentation analyses outcomes observed under aspects using RT-IoT2022 dataset. performance validation portrayed superior accuracy value 99.91% over existing approaches.

Language: Английский

---

Advanced quantum neural network-link net based intrusion detection framework and enhanced blowfish cryptography for data security

Intelligent Decision Technologies, Journal Year: 2025, Volume and Issue: unknown

Published: April 21, 2025

As cybersecurity threats evolve, it has become increasingly important to ensure data protection while successfully discovering intrusions. This paper introduces a novel Quantum Computation with Neural Networks for Intrusion Detection and Data Security (QCNN-IDDS) framework, which integrates advanced quantum computing neural network techniques intrusion detection encryption. The framework uses Quadratic Network (QNN) model complex, nonlinear relationships in data, improving performance. preprocessing is performed using the Double Normalization Technique (DNT), followed by feature extraction that incorporates statistical measures (e.g., mean, variance, skewness) assess relevance. process an Entropy Threshold Weighted (ETW-QNN) LinkNet classify as normal or abnormal. classified then encrypted Modulus-assisted Blowfish (MAB) algorithm, providing robust security. Evaluation on UNSW-NB15 dataset demonstrates ETW-QNN achieves peak accuracy of 0.917, outperforming models like CNN + LSTM GRU (0.747), (0.742), EfficientNet (0.743), ResNet (0.757), DNN lowest at 0.730. proposed offers significant improvements both security compared traditional methods. With its potential high low false positive rates, QCNN-IDDS expected enhance efficiency reliability real-world systems, paving way more robust, adaptive, scalable solutions dynamic high-traffic environments.

Language: Английский

---

Optimization of Intrusion Detection with Deep Learning: A Study Based on the KDD Cup 99 Database

International Journal of Safety and Security Engineering, Journal Year: 2024, Volume and Issue: 14(4), P. 1029 - 1038

Published: Aug. 30, 2024

With the exponential increase in cyberattacks, need for effective and scalable network intrusion detection systems (IDS) is critical.This study evaluates effectiveness of applying a deep neural model designed attack classification using KDD Cup 99 database.Our approach involves meticulous data preparation training optimization, which leads to notable improvements accuracy detecting various types attacks.The results highlight potential learning techniques significantly enhance IDS performance.This provides valuable insights into practical application security suggests avenues future research aimed at improving capabilities adapting emerging cyber threats.

Language: Английский

---

Deep learning based network intrusion detection system: a systematic literature review and future scopes

International Journal of Information Security, Journal Year: 2024, Volume and Issue: 23(6), P. 3433 - 3463

Published: Aug. 2, 2024

Language: Английский

---

Intrusion Detection Using Convolutional Neural Network: A Color Mapping Approach on NSL-KDD Dataset

Published: Dec. 19, 2024

Language: Английский

---