Hybrid dung beetle optimization based dimensionality reduction with deep learning based cybersecurity solution on IoT environment

Alexandria Engineering Journal, Journal Year: 2024, Volume and Issue: 111, P. 148 - 159

Published: Oct. 22, 2024

Language: Английский

---

Robust DDoS Attack Detection Using Piecewise Harris Hawks Optimizer with Deep Learning for a Secure Internet of Things Environment

Mathematics, Journal Year: 2023, Volume and Issue: 11(21), P. 4448 - 4448

Published: Oct. 27, 2023

The Internet of Things (IoT) refers to the network interconnected physical devices that are embedded with software, sensors, etc., allowing them exchange and collect information. Although IoT have several advantages can improve people’s efficacy, they also pose a security risk. malicious actor frequently attempts find new way utilize exploit specific resources, an device is ideal candidate for such exploitation owing massive number active devices. Especially, Distributed Denial Service (DDoS) attacks include considerable like devices, which act as bots transfer fraudulent requests services, thereby obstructing them. There needs be robust system detection based on satisfactory methods detecting identifying whether these occurred or not in network. most widely used technique purposes artificial intelligence (AI), includes usage Deep Learning (DL) Machine (ML) cyberattacks. study presents Piecewise Harris Hawks Optimizer Optimal Classifier (PHHO-ODLC) secure environment. fundamental goal PHHO-ODLC algorithm detect existence DDoS platform. method follows three-stage process. At initial stage, PHHO employed choose relevant features enhance classification performance. Next, attention-based bidirectional long short-term memory (ABiLSTM) applied attack Finally, hyperparameter selection ABiLSTM carried out by use grey wolf optimizer (GWO). A widespread simulation analysis was performed exhibit improved accuracy technique. extensive outcomes demonstrated significance regarding

Language: Английский

---

Ensemble Deep Learning Model based on Multi-Class Classification Technique to Detect Cyber Attacks in IoT Environment

Published: June 6, 2024

Language: Английский

---

Majority Voting Ensemble Classifier for Detecting Keylogging Attack on Internet of Things

IEEE Access, Journal Year: 2024, Volume and Issue: 12, P. 19860 - 19871

Published: Jan. 1, 2024

An intrusion attack on the Internet of Things (IoT) is any malicious activity or unauthorized access that jeopardizes integrity and security IoT systems, networks, devices. Regarding IoT, intrusions can result in severe problems, including service disruption, data theft, privacy violations, even bodily injury. One attacks a keylogging attack, sometimes referred to as keystroke logging keyboard capture, which type cyberattack attacker secretly observes records keystrokes made device's keyboard. In context where connected objects communicate exchange data, this assault may be especially concerning. Keylogging have repercussions ecosystem since they compromise sensitive information, login passwords, personal financial confidential communications. This paper explored possibility using an ensemble classifier detect networks. We built consisting three classifiers: convolutional neural network (CNN), recurrent (RNN), long-short memory (LSTM). A proposed model uses BoT-IoT dataset attack. Results show improve model's performance. The had excellent accuracy low false positive rate. It also significantly improved detection rates for than other classifiers.

Language: Английский

---

Experimental study on train axle fatigue crack acoustic emission signals recognition based on a one-dimensional convolutional neural network

Nondestructive Testing And Evaluation, Journal Year: 2024, Volume and Issue: unknown, P. 1 - 32

Published: Aug. 20, 2024

The method for identifying train axle fatigue cracks based on acoustic emission technology requires the classification and processing of signals. However, existing methods recognizing crack signals, including parameter analysis, wavelet traditional machine learning algorithms, usually rely expert experience, resulting in low detection efficiency. Additionally, algorithms above typically have shallow structures, which limits their ability to extract deeper feature information. Therefore, this paper proposes a that uses one-dimensional convolutional neural network (1D-CNN) identify This achieves end-to-end intelligent recognition eliminating need manual intervention or pre-set extractors. Furthermore, it leverages deep mechanisms deeply mine complex features within thereby enhancing accuracy model's identification. Experimental validation was conducted using signals collected from test rig. results demonstrate model can accurately cracks, achieving an identification over 99%. Meanwhile, compared with other models, effectiveness proposed is further verified.

Language: Английский

---

ECBoA-OFS: An Ensemble Classification Model for Botnet Attacks based on Optimal Feature Selection using CPR in IoT

Journal of Machine and Computing, Journal Year: 2024, Volume and Issue: unknown, P. 870 - 885

Published: Oct. 5, 2024

The rapid growth of the Internet Things (IoT) has indeed introduced new security challenges, and proliferation compromised IoT devices become a significant concern. Botnet attacks, where multiple corrupted are managed by particular object, have widespread threat in environments. These used for variety malicious activities, including distributed DDoS data breaches, malware distribution. However, detecting botnets poses several challenges due to resource constraints inherent many devices. limitations computation, storage, communication capabilities make it challenging deploy complex ML deep learning models directly on these This paper proposes an ensemble classification model ECBoA-OFS (Ensemble Classification Attack Prediction using Optimal Feature Selection). It focuses enhancing accuracy botnet attack prediction through integration methods optimal feature selection. describes method selection context analyzing behavior BoA traffic flow features network Central Pivot Ranges (CPR). is important step machine analysis because supports identification most given problem, thereby improving performance interpretation. extracted training prediction. To evaluate ECBoA-OFS, N-BaIoT-2021 dataset consisting regular records utilized, considering detection precision, sensitivity, specificity, accuracy, F1-score. Although all classifier achieved better selection, proposed ECBA-OFS shows results compared other results.

Language: Английский

---

Vulnerability Testing on IoT Networks Using Machine Learning Algorithm

Published: April 18, 2024

The increasing growth of Internet Things (IoT) devices has created a wide attack surface for cyber criminals to carry out more destructive attacks; therefore, the number attacks in information security industry is rapidly. As attackers use new and innovative methods launch cyber-oriented attacks, many these strikes have succeeded their malicious goals. Anomaly-based intrusion detection systems (IDS) machine learning techniques detect classify on IoT networks. Faced with unpredictable network technologies various infiltration methods, traditional are powerless. In abounding areas research, kernel prove that they accurately determine pathological abilities.

Language: Английский

---

Detection of DDoS Attack on Software-Defined Networking Controller Using Convolutional Neural Networks

Published: July 12, 2024

Language: Английский

---