Detecting attacks on the internet of things network in the computing fog layer with an embedded learning approach based on clustering and blockchain

Cluster Computing, Год журнала: 2025, Номер 28(4)

Опубликована: Фев. 25, 2025

Язык: Английский

---

Hybrid CNN–BiLSTM–DNN Approach for Detecting Cybersecurity Threats in IoT Networks

Computers, Год журнала: 2025, Номер 14(2), С. 58 - 58

Опубликована: Фев. 10, 2025

The Internet of Things (IoT) ecosystem is rapidly expanding. It driven by continuous innovation but accompanied increasingly sophisticated cybersecurity threats. Protecting IoT devices from these emerging vulnerabilities has become a critical priority. This study addresses the limitations existing threat detection methods, which often struggle with dynamic nature environments and growing complexity cyberattacks. To overcome challenges, novel hybrid architecture combining Convolutional Neural Networks (CNN), Bidirectional Long Short-Term Memory (BiLSTM), Deep (DNN) proposed for accurate efficient detection. model’s performance evaluated using IoT-23 Edge-IIoTset datasets, encompass over ten distinct attack types. framework achieves remarkable 99% accuracy on both outperforming state-of-the-art solutions. Advanced optimization techniques, including model pruning quantization, are applied to enhance deployment efficiency in resource-constrained environments. results highlight robustness its adaptability diverse scenarios, address key prior approaches. research provides robust solution detection, establishing foundation advancing security addressing evolving landscape cyber threats while driving future innovations field.

Язык: Английский

---

Intrusion defense: Leveraging ant colony optimization for enhanced multi-optimization in network security

Peer-to-Peer Networking and Applications, Год журнала: 2025, Номер 18(2)

Опубликована: Фев. 15, 2025

Язык: Английский

---

Enhancing network security with memory-augmented visual attention networks and predator–prey optimization models

Iran Journal of Computer Science, Год журнала: 2025, Номер unknown

Опубликована: Март 18, 2025

Язык: Английский

---

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

Intelligent Decision Technologies, Год журнала: 2025, Номер unknown

Опубликована: Апрель 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.

Язык: Английский

---

A Comparative Analysis of Anomaly Detection Methods in IoT Networks: An Experimental Study

Applied Sciences, Год журнала: 2024, Номер 14(24), С. 11545 - 11545

Опубликована: Дек. 11, 2024

The growth of the Internet Things (IoT) and its integration with Industry 4.0 5.0 are generating new security challenges. One key elements IoT systems is effective anomaly detection, which identifies abnormal behavior in devices or entire systems. This paper presents a comprehensive overview existing methods for detection networks using machine learning (ML). A detailed analysis various ML algorithms, both supervised (e.g., Random Forest, Gradient Boosting, SVM) unsupervised Isolation Autoencoder), was conducted. results tests conducted on popular datasets (IoT-23 CICIoT-2023) were collected analyzed detail. performance selected algorithms evaluated commonly used metrics (Accuracy, Precision, Recall, F1-score). experimental showed that Forest Autoencoder highly detecting anomalies. article highlights importance appropriate data preprocessing to improve accuracy. Furthermore, limitations centralized approach context distributed discussed. also potential directions future research field IoT.

Язык: Английский

---

CNN-GWO-voting & hybrid: ensemble learning inspired intrusion detection approaches for cyber-physical systems

DELETED, Год журнала: 2024, Номер unknown

Опубликована: Ноя. 26, 2024

Cyber threats are increasingly dynamic and sophisticated, often surpassing the capabilities of conventional intrusion detection systems (IDSs). Current IDSs for cyber-physical (CPSs) face limitations such as high computational complexity, low accuracy, elevated false positive rates. To address these challenges, two novel IDS approaches inspired by ensemble learning being proposed. The first approach, CNN-GWO-Voting, combines deep learning, evolutionary optimization, to enhance effectiveness. This approach introduces a hybrid model design with soft voting mechanism fitness function optimize attribute selection, distinguishing it from existing models. In this convolutional neural network (CNN) is used feature extraction, gray-wolf optimizer (GWO) selecting optimal attack relevant features, blend predictions four base classifiers: random forest, support vector machine (SVM), decision tree XGBoost. Evaluated on CIC-IoT-2023 dataset, achieves accuracy (99.15%), precision (0.99), recall F1-score FPR (0.008), FNR (0.008) while only 15 46 significantly reducing complexity. second comprehensive classifier binary classification, utilizing logistic regression, naïve bayes, SVM, k-nearest neighbour, multilayer perceptron classifiers, technique voting, stacking, bagging, boosting. On boosting yielded best results i.e. (98.16%), (0.98), (0.98). Both proposed not outperform recent advanced techniques but also introduce significant improvements in methodologies tailored specifically CPSs security.

Язык: Английский

---

A hybrid model for detecting intrusions using stacked autoencoders and extreme gradient boosting

Computers & Security, Год журнала: 2024, Номер unknown, С. 104212 - 104212

Опубликована: Ноя. 1, 2024

Язык: Английский

---

Optimizing Intrusion Detection for DoS, DDoS, and Mirai Attacks Subtypes Using Hierarchical Feature Selection and CatBoost on the CICIoT2023 Dataset

Data & Metadata, Год журнала: 2024, Номер 3, С. 577 - 577

Опубликована: Дек. 17, 2024

Introduction: Modern networks suffer until unheard of vulnerabilities that need for advanced intrusion detection systems (IDS) given the growing danger presented by DoS, DDoS, and Mirai attacks. Research on identification certain attack subtypes is still lacking even with CICIoT2023 dataset, which offers a complete basis evaluating these cyber hazards. Usually, aggregating attacks into more general categories, existing research neglects complex characteristics specific subtypes, therefore reducing effectiveness.Methods: This work presents novel IDS model aiming at high accuracy subtypes. Using hierarchical feature selection CatBoost algorithm our addresses problems high-dimensional data emphasizes keeping most important features means preprocessing methods including Spearman correlation clustering. Furthermore, used stratified sampling to guarantee in training testing stages fair representation types, both common uncommon.Results: With an amazing Prediction Time per Network Flow 7.16e-07 seconds, shows breakthrough performance rigorous cross-valuation, thereby attaining outstanding outcomes accuracy, recall, precision.Conclusions: Our method not only closes significant gap current knowledge but also establishes new benchmark cybersecurity providing very detailed protection mechanisms against threats. study marks major progress network security as it gives companies efficient instrument recognize minimize risks better precision effectiveness

Язык: Английский

---

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

Опубликована: Дек. 19, 2024

Язык: Английский

---