A novel feature selection-driven ensemble learning approach for accurate botnet attack detection

Alexandria Engineering Journal, Journal Year: 2025, Volume and Issue: 118, P. 261 - 277

Published: Jan. 22, 2025

Language: Английский

---

Network Intrusion Detection System Using Convolutional Neural Networks: NIDS-DL-CNN for IoT Security

Cluster Computing, Journal Year: 2025, Volume and Issue: 28(4)

Published: Feb. 25, 2025

Language: Английский

---

Enhanced botnet detection in IoT networks using zebra optimization and dual-channel GAN classification

Scientific Reports, Journal Year: 2024, Volume and Issue: 14(1)

Published: July 26, 2024

The Internet of Things (IoT) permeates various sectors, including healthcare, smart cities, and agriculture, alongside critical infrastructure management. However, its susceptibility to malware due limited processing power security protocols poses significant challenges. Traditional antimalware solutions fall short in combating evolving threats. To address this, the research work developed a feature selection-based classification model. At first stage, preprocessing stage enhances dataset quality through data smoothing consistency improvement. Feature selection via Zebra Optimization Algorithm (ZOA) reduces dimensionality, while phase integrates Graph Attention Network (GAN), specifically Dual-channel GAN (DGAN). DGAN incorporates Node Networks Semantic capture intricate IoT device interactions detect anomalous behaviors like botnet activity. model's accuracy is further boosted by leveraging both structural semantic with Sooty Tern (STOA) for hyperparameter tuning. proposed STOA-DGAN model achieves an impressive 99.87% activity classification, showcasing robustness reliability compared existing approaches.

Language: Английский

---

AI-based model for securing cognitive IoT devices in advance communication systems

International Journal of Cognitive Computing in Engineering, Journal Year: 2025, Volume and Issue: unknown

Published: Feb. 1, 2025

Language: Английский

---

Generalizability Assessment of Learning‐Based Intrusion Detection Systems for IoT Security: Perspectives of Data Diversity

Security and Privacy, Journal Year: 2025, Volume and Issue: 8(2)

Published: March 1, 2025

ABSTRACT Machine learning (ML) and deep (DL) models have become vital tools in Intrusion Detection Systems (IDS), yet their effectiveness depends heavily on the quality distribution of training data. This study investigates impact dataset size balance performance ML DL using CIC‐IDS 2017 dataset. Five subsets (20%, 40%, 60%, 80%, 100% dataset) were created to assess across varying sizes. Four models, including Random Forest (RF), Artificial Neural Network, Convolutional Network (CNN), CNN+Long‐Term Short Memory (CNN+LSTM), trained evaluated these subsets, focusing precision, recall, F1‐score. To test model generalizability, a synthetic 20 million over‐sampled samples was generated Synthetic Minority Oversampling Technique, followed by manual under‐sampling create balanced 1.5 with approximately 100 000 per attack class. Upon generalizability assessment already synthetically datasets, CNN+LSTM consistently outperformed other but utilized more time for testing each case. The RF showed weakest performances fastest both scenarios. Moreover, evaluate importance general particular, we also considered NSL‐KDD all four multiple classifications binary classification. Our results highlight dataset, structure models.

Language: Английский

---

Detecting and Analyzing Botnet Nodes via Advanced Graph Representation Learning Tools

Algorithms, Journal Year: 2025, Volume and Issue: 18(5), P. 253 - 253

Published: April 26, 2025

Private consumers, small businesses, and even large enterprises are all at risk from botnets. These botnets known for spearheading Distributed Denial-Of-Service (DDoS) attacks, spamming populations of users, causing critical harm to major organizations. The development Internet Things (IoT) devices led the use these cryptocurrency mining, in-transit data interception, sending logs containing private master botnet. Different techniques were developed identify botnet activities, but only a few Graph Neural Networks (GNNs) analyze host activity by representing their communications with directed graph. Although GNNs intended extract structural graph properties, they overfitting, which leads failure when attempting do so an unidentified network. In this study, we test notion that patterns might be used efficient detection. also present SIR-GN, iterative representation learning methodology nodes. Our approach is built work well untested data, our model able provide vector every node captures its information. Finally, demonstrate that, collection vectors incorporated into neural network classifier, outperforms state-of-the-art GNN-based algorithms in detection bot nodes within unknown networks.

Language: Английский

---

Semantic Web-Driven Targeted Adversarial Attack on Black Box Automatic Speech Recognition Systems

International Journal on Semantic Web and Information Systems, Journal Year: 2024, Volume and Issue: 20(1), P. 1 - 23

Published: Nov. 15, 2024

The susceptibility of Deep Neural Networks (DNNs) to adversarial attacks in Automatic Speech Recognition (ASR) systems has drawn significant attention. Most work focuses on white-box methods, but the assumption full transparency model architecture and parameters is unrealistic real-world scenarios. Although several targeted black-box attack methods have been proposed recent years, due complexity ASR systems, they primarily rely query-based approaches with limited search capabilities, leading low success rates noticeable noise. To address this, we propose DE-gradient, a new approach using differential evolution (DE), population-based algorithm. Inspired by Semantic Web ideas, introduce modulation noise preserve semantic coherence while enhancing imperceptibility. In experiments two public datasets, DE-gradient improved 19% increased signal-to-noise ratio (SNR) silent parts from 27 dB 54 dB, establishing strong baseline for evaluating systems.

Language: Английский

---

A survey of transmission control protocol variants

World Journal of Advanced Research and Reviews, Journal Year: 2024, Volume and Issue: 21(3), P. 1828 - 1853

Published: March 26, 2024

TCP (Transmission Control Protocol), is a reliable connection oriented end-to-end protocol. It contains within itself, mechanisms for ensuring reliability by requiring the receiver to acknowledge segments that it receives. The network not perfect and small percentage of packets are lost enroute, either due error or fact there congestion in routers dropping packets. ensures starting timer whenever sends segment. If does receive an acknowledgement from ‘time-out’ interval then retransmits In this paper review various carried out. There number variants application management efficiency terms transmission efficiency. These include: - Tahoe, Reno, New Vegas, SACK, FACK, Asym, RBP, Full CUBIC. Therefore, main objective study tcp types on performance variances. All have different features advantages but with maximal throughput as objective, which termed clones TCP, been incorporated into TCP/IP protocol handling efficiently scenarios.

Language: Английский

---

COMPUTATIONALLY EFFICIENT DEEP FEDERATED LEARNING WITH OPTIMIZED FEATURE SELECTION FOR IOT BOTNET DETECTION

Intelligent Systems with Applications, Journal Year: 2024, Volume and Issue: unknown, P. 200462 - 200462

Published: Nov. 1, 2024

Language: Английский

---