Mitigating DDoS Attacks in Virtual Machine Migration: An In-Depth Security Framework Utilizing Deep Learning and Advanced Encryption Techniques DOI

V. N.,

V. S. Shankar Sriram

International Journal of Innovative Technology and Exploring Engineering, Год журнала: 2025, Номер 14(2), С. 12 - 20

Опубликована: Янв. 25, 2025

Safeguarding virtual machines (VMs) during migration is essential to avert Service Level Agreement (SLA) violations. This research article presents a robust security framework that utilizes deep learning and advanced encryption methods reduce the impact of Distributed Denial (DDoS) attacks machine migration. The study introduces an Improved Sparrow Search Algorithm-based Deep Neural Network (ISSA-DNN) for classification DDoS Advanced Encryption Standard-Elliptic Curve Cryptography (AES-ECC) safeguard images. primary objective mitigate risks associated with VM by identifying safeguarding VMs using cryptographic techniques. employs Canadian Institute Cybersecurity (CICDDoS) dataset, implementing preprocessing procedures like duplication elimination, feature selection via Random Forest, normalization improve precision DNN classifier. ISSA-DNN approach enhances hyperparameter optimization inverse mutation-based sparrow search, yielding precise attack model. Furthermore, incorporates AES-ECC encrypting images, amalgamating AES's computational efficiency ECCs improved security. In contrast conventional methods, this hybrid throughput decreases decryption durations, rendering it appropriate high-throughput real-time applications. Experimental findings indicate proposed attains accuracy 98.79%, surpassing current state-of-the-art technique markedly performance metrics, proactive policy safeguards sensitive data guarantees adherence regulatory standards. conclusion, established offers comprehensive solution mitigating methodologies. Integrating strategy improving cybersecurity in cloud environments.

Язык: Английский

A Comprehensive Survey: Evaluating the Efficiency of Artificial Intelligence and Machine Learning Techniques on Cyber Security Solutions DOI Creative Commons
Merve Ozkan-Okay, Erdal Akin, Ömer Aslan

и другие.

IEEE Access, Год журнала: 2024, Номер 12, С. 12229 - 12256

Опубликована: Янв. 1, 2024

Given the continually rising frequency of cyberattacks, adoption artificial intelligence methods, particularly Machine Learning (ML), Deep (DL), and Reinforcement (RL), has become essential in realm cybersecurity. These techniques have proven to be effective detecting mitigating which can cause significant harm individuals, organizations, even countries. learning algorithms use statistical methods identify patterns anomalies large datasets, enabling security analysts detect previously unknown threats. learning, a subfield ML, shown great potential improving accuracy efficiency cybersecurity systems, image speech recognition. On other hand, RL is again machine that trains learn through trial error, making it dynamic environments. We also evaluated usage ChatGPT-like AI tools cyber-related problem domains on both sides, positive negative. This article provides an overview how DL, are applied cybersecurity, including their malware detection, intrusion vulnerability assessment, areas. The state-of-the-art studies using models each section based main idea, techniques, important findings. It discusses these techniques' challenges limitations, data quality, interpretability, adversarial attacks. Overall, holds promise for effectiveness systems enhancing our ability protect against cyberattacks. However, continue developing refining address ever-evolving nature cyber Besides, some promising solutions rely deep reinforcement susceptible attacks, underscoring importance factoring this when devising countermeasures sophisticated concluded ChatGPT valuable tool but should noted manipulated threaten integrity, confidentiality, availability data.

Язык: Английский

Процитировано

56
Detecting DDoS attacks using adversarial neural network DOI Creative Commons

Ali Mustapha,

Rida Khatoun,

Sherali Zeadally

и другие.

Computers & Security, Год журнала: 2023, Номер 127, С. 103117 - 103117

Опубликована: Янв. 26, 2023

Язык: Английский

Процитировано

44
Advancing cybersecurity: a comprehensive review of AI-driven detection techniques DOI Creative Commons

A Salem,

Safaa M. Azzam,

O. E. Emam

и другие.

Journal Of Big Data, Год журнала: 2024, Номер 11(1)

Опубликована: Авг. 4, 2024

Abstract As the number and cleverness of cyber-attacks keep increasing rapidly, it's more important than ever to have good ways detect prevent them. Recognizing cyber threats quickly accurately is crucial because they can cause severe damage individuals businesses. This paper takes a close look at how we use artificial intelligence (AI), including machine learning (ML) deep (DL), alongside metaheuristic algorithms better. We've thoroughly examined over sixty recent studies measure effective these AI tools are identifying fighting wide range threats. Our research includes diverse array cyberattacks such as malware attacks, network intrusions, spam, others, showing that ML DL methods, together with algorithms, significantly improve well find respond We compare methods out what they're where could improve, especially face new changing cyber-attacks. presents straightforward framework for assessing Methods in threat detection. Given complexity threats, enhancing regularly ensuring strong protection critical. evaluate effectiveness limitations current proposed models, addition algorithms. vital guiding future enhancements. We're pushing smart flexible solutions adapt challenges. The findings from our suggest protecting against will rely on continuously updating stay ahead hackers' latest tricks.

Язык: Английский

Процитировано

32
Building a Cloud-IDS by Hybrid Bio-Inspired Feature Selection Algorithms Along With Random Forest Model DOI Creative Commons
Mhamad Bakro, Rakesh Ranjan Kumar, M. N. Husain

и другие.

IEEE Access, Год журнала: 2024, Номер 12, С. 8846 - 8874

Опубликована: Янв. 1, 2024

The adoption of cloud computing has become increasingly widespread across various domains. However, the inherent security vulnerabilities pose significant risks to its overall safety. Consequently, intrusion detection systems (IDS) play a pivotal role in identifying malicious activities within system. considerable volume network traffic data may contain redundant and irrelevant features that can impact classification performance classifier. In addition, complexity time consumption increase while processing such substantial process. To enhance IDS, this study proposes hybrid feature selection approach, combining two bio-inspired algorithms, namely grasshopper optimization algorithm (GOA) genetic (GA). combination these algorithms ensures more efficient search for optimal solutions. A random forest (RF) classifier is trained using those features. Moreover, proposal addresses challenge imbalanced by employing approach: over-sampling minority classes an adaptive synthetic (ADASYN) algorithm, implementing under-sampling (RUS) majority class as needed. This integrated strategy significantly influences each category, enhancing true positive rate (TPR) minimizing false (FPR), thus improving system performance. proposed approach was evaluated three datasets: UNSW-NB15, CIC-DDoS2019, CIC Bell DNS EXF 2021. recorded accuracies datasets were 98%, 99%, 92%, respectively. selection-based IDS demonstrated superior multi-class classification, along with exemplary results individual datasets. exhibited marked superiority classifier, especially when compared other classifiers including SVM, LR, FLN, LSTM, AlexNet, DNN, DBN, DT, XGBoost. remained consistent commendable even benchmarked against contemporary state-of-the-art methodologies multiple evaluation metrics.

Язык: Английский

Процитировано

17
Deep Learning Models with Transfer Learning and Ensemble for Enhancing Cybersecurity in IoT Use Cases DOI Open Access

Sivananda Hanumanthu,

G. Anil Kumar

International Journal of Computational and Experimental Science and Engineering, Год журнала: 2025, Номер 11(1)

Опубликована: Фев. 28, 2025

Internet of Things (IoT) applications have made inroads into different domains, providing unique solutions—Internet technology offers seamless integration physical and digital worlds. However, the broad nature technologies protocols used in IoT has increased vulnerability from malicious attackers. Hence, protecting cyber-attacks is imperative. Researchers implemented intrusion detection systems to overcome this issue improve cybersecurity scenarios. With new threats cybercrime emerging, a continuous effort required enhance security applications. To address pressing need, we present our study that proposes deep learning-based framework bolster at use cases level by exploiting power transfer learning ensembling it models pre-trained larger datasets. Deep attain high performance with help hyperparameter tuning, achieve through PSO proposed system. Our ensemble system shows how individual can outperform using best-performing as constituents approach. We introduce an algorithm called — Optimized Ensemble Learning-Based Intrusion Detection (OEL-ID). This leverages corresponding optimization strategies boost for improved cyber Using UNSW-NB15 benchmark dataset, empirical demonstrates method, compared some existing models, obtained accuracy 98.89%, which, turn, provided highest comparative accuracy. Therefore, be allows significant system's underlying

Язык: Английский

Процитировано

4
An intelligent DDoS attack detection tree-based model using Gini index feature selection method DOI
Mohamed Aly Bouke, Azizol Abdullah,

Sameer Hamoud ALshatebi

и другие.

Microprocessors and Microsystems, Год журнала: 2023, Номер 98, С. 104823 - 104823

Опубликована: Март 23, 2023

Язык: Английский

Процитировано

36
A DDoS Detection Method Based on Feature Engineering and Machine Learning in Software-Defined Networks DOI Creative Commons
Zhenpeng Liu,

Yihang Wang,

Fan Feng

и другие.

Sensors, Год журнала: 2023, Номер 23(13), С. 6176 - 6176

Опубликована: Июль 5, 2023

Distributed denial-of-service (DDoS) attacks pose a significant cybersecurity threat to software-defined networks (SDNs). This paper proposes feature-engineering- and machine-learning-based approach detect DDoS in SDNs. First, the CSE-CIC-IDS2018 dataset was cleaned normalized, optimal feature subset found using an improved binary grey wolf optimization algorithm. Next, trained tested Random Forest (RF), Support Vector Machine (SVM), K-Nearest Neighbor (k-NN), Decision Tree, XGBoost machine learning algorithms, from which best classifier selected for attack detection deployed SDN controller. The results show that RF performs when compared across several performance metrics (e.g., accuracy, precision, recall, F1 AUC values). We also explore comparison between different models algorithms. our proposed method performed can effectively identify SDNs, providing new idea solution security of

Язык: Английский

Процитировано

29
Sin-Cos-bIAVOA: A new feature selection method based on improved African vulture optimization algorithm and a novel transfer function to DDoS attack detection DOI

Zakieh Sharifian,

Behrang Barekatain, Alfonso Ariza Quintana

и другие.

Expert Systems with Applications, Год журнала: 2023, Номер 228, С. 120404 - 120404

Опубликована: Май 10, 2023

Язык: Английский

Процитировано

23
Cybersecurity in the AI era: analyzing the impact of machine learning on intrusion detection DOI
Huiyao Dong, Igor Kotenko

Knowledge and Information Systems, Год журнала: 2025, Номер unknown

Опубликована: Фев. 19, 2025

Язык: Английский

Процитировано

1
A novel detection model for abnormal network traffic based on bidirectional temporal convolutional network DOI
Jinfu Chen,

Tianxiang Lv,

Saihua Cai

и другие.

Information and Software Technology, Год журнала: 2023, Номер 157, С. 107166 - 107166

Опубликована: Фев. 1, 2023

Язык: Английский

Процитировано

19