Cloud-based intrusion detection using kernel fuzzy clustering and optimal type-2 fuzzy neural network

Srilatha, Doddi; Shyam, Gopal K.

doi:10.1007/s10586-021-03281-9

Cited by 16 publications

(10 citation statements)

References 14 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…First, the performance of the DL-based ID models is evaluated in terms of f-measure, accuracy, false alarm rate, and training time. The existing models taken for comparison are T2FNN [19], ensemble model [20], BP-NN [21], SVNN [22], and HLDNS [23]. Each existing model uses different datasets for ID and different working platforms with unique configurations for performance analysis.…”

Section: Resultsmentioning

confidence: 99%

“…Doddi Srilatha and Gopal K. Shyam [19] developed the cloud-based IDS that combined kernel fuzzy c-means clustering (KFCM) and an ideal type-2 fuzzy neural network (OT2FNN). T2FNN parameters were optimally selected for weight optimization employing the lion optimization technique (LOA).…”

Section: Intrusion Detection Frameworkmentioning

confidence: 99%

“…This section highlights the problems faced by the existing models in cloud security and in ID frameworks. The models used in ID frameworks [19][20][21][22][23], mostly used optimization mechanisms in the weight selection of the classifier and they did not focus on developing efficient feature selection mechanisms for classifiers. This will increases the training time of the classifier for classifying the intrusions, so the performance of the classifier is degraded with overfitting issues and lesser accuracy.…”

Section: Problem Statementmentioning

confidence: 99%

See 2 more Smart Citations

An Improved Ecc Algorithm for Secure Cloud Storage System With the Help of Sha-256 Based User Authentication and Deep Learning Based Intrusion Detection System

Samy

Mary

2022

Preprint

View full text Add to dashboard Cite

A cloud environment is a collection of resources used to provide on-demand services to cloud clients. Access to the cloud environment is supplied through internet services, and data kept in the cloud environment is more accessible to both internal and external invaders. At the moment, cloud security experts are unable to provide a more dependable, safe, and effective intrusion detection system (IDS) for identifying intruders in data transfer. For fulfilling this requirement, in this paper a novel deep learning (DL) model namely Wavelet Kernel including Multi-Layer Perceptron Neural Network (WKMLPNN) based IDS is proposed for identifying the attacks while performing cloud data transmission. Additionally, to offer cloud secure storage, Improved Elliptical Curve Cryptography (IECC) is proposed with a novel key generation mechanism. Initially, the cloud user or data owner (DO) is registered with the Cloud Service Provider (CSP) for uploading their data to the cloud. Then at the CSP end, the authenticity of the DO is checked by implementing the Secure Hash Algorithm 256 (SHA-256) technique. After successful authentication, the DO is allowed to upload their data to the cloud. The CSP receives the data from the DO and then the intrusion present in the received data is identified using novel IDS (WKMLPNN). The presented IDS follows three operations such as preprocessing, optimal feature selection using Time factor incorporated Gravitational Search Algorithm (TGSA) and WKMLPNN applied classification for identifying the intrusions present in the data. If the received data contain the intrusion, the data will be avoided and not stored in the cloud, otherwise, the data will be stored in the cloud securely using the IECC algorithm. Finally, if the cloud users request CSP for data retrieval, the authenticity of the user is again checked using the SHA-256 algorithm. If the user is an authenticated one, the retrieval permission is granted for him, otherwise, the permission is denied for the user. The simulation results reveal that the presented approach outperforms existing strategies for intrusion categorization and encryption.

show abstract

Section: Resultsmentioning

confidence: 99%

Section: Intrusion Detection Frameworkmentioning

confidence: 99%

Section: Problem Statementmentioning

confidence: 99%

See 1 more Smart Citation

An Improved Ecc Algorithm for Secure Cloud Storage System With the Help of Sha-256 Based User Authentication and Deep Learning Based Intrusion Detection System

Samy

Mary

2022

Preprint

View full text Add to dashboard Cite

show abstract

“…Srilatha et al 25 OT2FNN, KFCM Automatically detect the attack data, including low frequent attacks and new attacks.…”

Section: References Approaches Used Advantages Disadvantagesmentioning

confidence: 99%

“…Srilatha et al 25 had developed an IDS system by combining an optimal type‐2 fuzzy neural network (T2FNN) and kernel fuzzy c‐means clustering (KFCM) for detecting low frequent attacks. By combining these approaches, clustering was formed in which attacks such as remote‐to‐local (R2L), DoS, user‐to‐root (U2R), and probe were detected.…”

Section: Related Workmentioning

confidence: 99%

Hybrid one‐dimensional residual autoencoder and ensemble of gradient boosting for cloud IDS

Chauhan,

Dwivedi

2024

Concurrency and Computation

View full text Add to dashboard Cite

SummaryThe distributed and decentralized architecture of cloud computing is important for a number of industries, including business, government, entertainment, education, and information technology. It facilitates a wide aspect of information technology, where the computing model is vulnerable to attacks or intrusion. For detecting malicious activities, a novel intrusion detection system (IDS) is required to be developed. In this paper, an enhanced synthetic minority oversampling technique (SMOTE) with a hybrid one‐dimensional residual auto encoder and the Ensemble of Gradient Boosting (1D‐RAE‐EGB) models are proposed for cloud intrusion detection. The proposed IDS resolves the class imbalance problem through enhanced SMOTE. In addition, noise reduction is accomplished with ID‐RAE, which minimizes the data dimension. Finally, the soft voting‐based ensemble classification model is used for attack detection. The ensemble gradient boosting model comprises categorical boosting (CatBoost), extreme gradient boosting (XGBoost), and light gradient boosting machine (LightGBM). The ensemble model is fine‐tuned by reducing the number of parameters under fitting conditions since it is not compulsory to re‐adjust the weight values in a backpropagation process. The proposed IDS is implemented in Python using the NSL‐KDD dataset. The accuracy, precision, recall, f1‐score, false positive rate (FPR), false negative rate (FNR), specificity, and Kappa measure obtained for the proposed IDS are 99.98%, 99.3%, 98.5%, 99.95%, 0.723, 0.46, 99.98%, and 99.97%, respectively.

show abstract

A Study on Swarm-Based Approaches for Intrusion Detection System in Cloud Environment

Nishika

Solanki

Dalal

2023

Lecture Notes in Networks and Systems

View full text Add to dashboard Cite

Cloud-based intrusion detection using kernel fuzzy clustering and optimal type-2 fuzzy neural network

Cited by 16 publications

References 14 publications

An Improved Ecc Algorithm for Secure Cloud Storage System With the Help of Sha-256 Based User Authentication and Deep Learning Based Intrusion Detection System

An Improved Ecc Algorithm for Secure Cloud Storage System With the Help of Sha-256 Based User Authentication and Deep Learning Based Intrusion Detection System

Hybrid one‐dimensional residual autoencoder and ensemble of gradient boosting for cloud IDS

A Study on Swarm-Based Approaches for Intrusion Detection System in Cloud Environment

Contact Info

Product

Resources

About