SmFD: Machine Learning Controlled Smart Factory Management Through IoT DDoS Device Identification DOI

Ankita Kumari,

Ishu Sharma

Published: Jan. 4, 2024

To prevent a website, network, or device from operating, Distributed Denial of Service (DDoS) attacks transmits large amount data to it. This attack makes use "botnet," which is an enormous collection pilfered devices that simultaneously transmit massive requests and the target system. In smart factory management, where lot are linked each other via Internet Things (IoT), DoS could be very risky. IoT essential factories, but these hacks have ability make them useless, might unfavorable effects. Downtime serious problem because it prevents (IoT) working, slows down production raises costs. DDoS may employed as diversion riskier behaviors compromise security, such unauthorized access breaches. Additionally, corruption loss occur, harming business's reputation long-term operations. proposed model ML trained chip systems capable real-time analysis. They identify patterns typical activity immediately anomalies indicate attacks. These not only trigger alerts, they also assist in identifying compromised devices, enabling prompt efficient action safety measures. The can manage new threats continually adapting learning things. building's managers security personnel see on basic screen. this research study, four distinct methodologies were used. Each provided unique method for approaching challenges related machine categorization. XGBoost, K-Nearest Neighbors (KNN), Logistic Regression, Gaussian Naive Bayes among techniques investigation's conclusions XGBoost stood out top performer continuously produced best results showed exceptional performance throughout range tasks assessed.

Language: Английский

Botnets Unveiled: A Comprehensive Survey on Evolving Threats and Defense Strategies DOI Open Access
Mehdi Asadi, Mohammad Ali Jabraeil Jamali, Arash Heidari

et al.

Transactions on Emerging Telecommunications Technologies, Journal Year: 2024, Volume and Issue: 35(11)

Published: Oct. 20, 2024

ABSTRACT Botnets have emerged as a significant internet security threat, comprising networks of compromised computers under the control command and (C&C) servers. These malevolent entities enable range malicious activities, from denial service (DoS) attacks to spam distribution phishing. Each bot operates binary code on vulnerable hosts, granting remote attackers who can harness combined processing power these hosts for synchronized, highly destructive while maintaining anonymity. This survey explores botnets their evolution, covering aspects such life cycles, C&C models, botnet communication protocols, detection methods, unique environments operate in, strategies evade tools. It analyzes research challenges future directions related botnets, with particular focus evasion techniques, including methods like encryption use covert channels reinforcement botnets. By reviewing existing research, provides comprehensive overview origins evolving tactics, evaluates how counteract activities. Its primary goal is inform community about changing landscape in combating threats, offering guidance addressing concerns effectively through highlighting methods. The concludes by presenting directions, using strengthen aims guide researchers developing more robust measures combat effectively.

Language: Английский

Citations

14
Improvement of Distributed Denial of Service Attack Detection through Machine Learning and Data Processing DOI Creative Commons
Fray L. Becerra-Suarez, Ismael Fernández-Roman, Manuel G. Forero

et al.

Mathematics, Journal Year: 2024, Volume and Issue: 12(9), P. 1294 - 1294

Published: April 25, 2024

The early and accurate detection of Distributed Denial Service (DDoS) attacks is a fundamental area research to safeguard the integrity functionality organizations’ digital ecosystems. Despite growing importance neural networks in recent years, use classical techniques remains relevant due their interpretability, speed, resource efficiency, satisfactory performance. This article presents results comparative analysis six machine learning techniques, namely, Random Forest (RF), Decision Tree (DT), AdaBoost (ADA), Extreme Gradient Boosting (XGB), Multilayer Perceptron (MLP), Dense Neural Network (DNN), for classifying DDoS attacks. CICDDoS2019 dataset was used, which underwent data preprocessing remove outliers, 22 features were selected using Pearson correlation coefficient. RF classifier achieved best accuracy rate (99.97%), outperforming other classifiers even previously published network-based techniques. These findings underscore feasibility effectiveness algorithms field attack detection, reaffirming relevance as valuable tool advanced cyber defense.

Language: Английский

Citations

9
An empirical study of pattern leakage impact during data preprocessing on machine learning-based intrusion detection models reliability DOI
Mohamed Aly Bouke, Azizol Abdullah

Expert Systems with Applications, Journal Year: 2023, Volume and Issue: 230, P. 120715 - 120715

Published: June 8, 2023

Language: Английский

Citations

22
Adversarial learning for Mirai botnet detection based on long short-term memory and XGBoost DOI Creative Commons
Vajratiya Vajrobol, Brij B. Gupta, Akshat Gaurav

et al.

International Journal of Cognitive Computing in Engineering, Journal Year: 2024, Volume and Issue: 5, P. 153 - 160

Published: Jan. 1, 2024

In today's world, where digital threats are on the rise, one particularly concerning threat is Mirai botnet. This malware designed to infect and command a collection of Internet Things (IoT) devices. The use attacks has intensified in recent times, thus threatening smooth operation numerous devices that connected network. Such carry adverse consequences include interference with services or leakage confidential information. To fight this growing threat, smart flexible detection techniques required counter new methods cyber attackers use. aim research develop resilient defense against botnet attacks. Long Short Term Memory term (LSTM) XGBoost combined have best performance 97.7% accuracy score. With combination, strengthen our defenses sophisticated dynamically operating botnets further enhance security world.

Language: Английский

Citations

8
Enhancing network intrusion detection performance using generative adversarial networks DOI
Xinxing Zhao,

Kar Wai Fok,

Vrizlynn L. L. Thing

et al.

Computers & Security, Journal Year: 2024, Volume and Issue: 145, P. 104005 - 104005

Published: July 20, 2024

Language: Английский

Citations

7
Model Design of Intrusion Detection System on Web Server Using Machine Learning Based DOI Open Access
Agus Tedyyana, Osman Ghazali, Onno W. Purbo

et al.

Published: Jan. 1, 2024

In the current era of information technology development, web server security has become a primary concern in maintaining data integrity, confidentiality, and availability. With emergence increasingly complex evolving cyber threats, Intrusion Detection Systems (IDS) play crucial role

Language: Английский

Citations

6
Deep Convolutional Generative Adversarial Networks in Image-Based Android Malware Detection DOI Creative Commons
Francesco Mercaldo, Fabio Martinelli, Antonella Santone

et al.

Computers, Journal Year: 2024, Volume and Issue: 13(6), P. 154 - 154

Published: June 19, 2024

The recent advancements in generative adversarial networks have showcased their remarkable ability to create images that are indistinguishable from real ones. This has prompted both the academic and industrial communities tackle challenge of distinguishing fake genuine We introduce a method assess whether generated by networks, using dataset real-world Android malware applications, can be distinguished actual images. Our experiments involved two types deep convolutional utilize derived static analysis (which does not require running application) dynamic application). After generating images, we trained several supervised machine learning models determine if these classifiers differentiate between malicious applications. results indicate that, despite being visually human eye, were correctly identified classifier with an F-measure approximately 0.8. While most accurately recognized as fake, some not, leading them considered produced

Language: Английский

Citations

6
Anomaly and intrusion detection using deep learning for software-defined networks: A survey DOI
Vitor Gabriel da Silva Ruffo, Daniel Matheus Brandão Lent, Mateus Komarchesqui

et al.

Expert Systems with Applications, Journal Year: 2024, Volume and Issue: 256, P. 124982 - 124982

Published: Aug. 5, 2024

Language: Английский

Citations

6
Digital Health Dashboards for Decision-Making to Enable Rapid Responses During Public Health Crises: Replicable and Scalable Methodology DOI Creative Commons
Tarun Reddy Katapally, Sheriff Tolulope Ibrahim

JMIR Research Protocols, Journal Year: 2023, Volume and Issue: 12, P. e46810 - e46810

Published: June 6, 2023

The COVID-19 pandemic has reiterated the need for cohesive, collective, and deliberate societal efforts to address inherent inefficiencies in our health systems overcome decision-making gaps using real-time data analytics. To achieve this, decision makers independent secure digital platforms that engage citizens ethically obtain big data, analyze convert into evidence, finally, visualize this evidence inform rapid decision-making.The objective of study is develop replicable scalable jurisdiction-specific dashboards monitor, mitigate, manage public crises via integration beyond care.The primary approach development dashboard was use global citizen science tackle pandemics like COVID-19. first step process establish an 8-member Citizen Scientist Advisory Council Digital Epidemiology Population Health Laboratory's community partnerships. Based on consultation with council, three critical needs were prioritized: (1) management household risk COVID-19, (2) facilitation food security, (3) understanding accessibility services. Thereafter, a progressive web application (PWA) developed provide daily services these needs. generated from access PWA are set up be anonymized, aggregated, linked decision-making, is, displays anonymized aggregated obtained devices PWA. hosted Amazon Elastic Compute Cloud server. dashboard's interactive statistical navigation designed Microsoft Power Business Intelligence tool, which creates connection Relational Database server regularly update visualization jurisdiction-specific, data.The resulted decision-making. relayed real time reflect usage provides households ability their request when need, report difficulties issues accessing also delegated alert system risks time, bidirectional engagement allows respond queries, enhanced security.Digital can transform policy by prioritizing as well enable directly communicate mitigate existing emerging crises, paradigm-changing approach, inverting innovation needs, advancing equity.RR1-10.2196/46810.

Language: Английский

Citations

15
An Unsupervised Generative Adversarial Network System to Detect DDoS Attacks in SDN DOI
Daniel Matheus Brandão Lent, Vitor Gabriel da Silva Ruffo, Luiz F. Carvalho

et al.

IEEE Access, Journal Year: 2024, Volume and Issue: 12, P. 70690 - 70706

Published: Jan. 1, 2024

Network management is a crucial task to maintain modern systems and applications running.Some have become vital for society are expected zero downtime.Software-defined networks paradigm that collaborates with the scalability, modularity manageability of by centralizing network's controller.However, this creates weak point distributed denial service attacks if unprepared.This study proposes an anomaly detection system detect in software-defined using generative adversarial neural gated recurrent units.The proposed uses unsupervised learning unknown interval 1 second.A mitigation algorithm also stop denial-of-service from harming operation.Two datasets were used validate model: first developed computer group Orion State University Londrina.The second well-known dataset: CIC-DDoS2019, widely community.Besides units, other types neurons tested work, they are: long short-term memory, convolutional temporal convolutional.The module reached F1-score 99% dataset 98% second, while could drop malicious flows both datasets.

Language: Английский

Citations

5