RETRACTED: An intrusion identification and prevention for cloud computing: From the perspective of deep learning

Kumar, Anil; Umurzoqovich, Rajabov Sherzod; Duong, Nguyen Phuc; Kanani, Pratik; Kuppusamy, Arulmani; Praneesh, M.; Hieu, Minh Nguyen

doi:10.1016/j.ijleo.2022.170044

Cited by 30 publications

(11 citation statements)

References 26 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…But when the number or relative size of the criteria increases, the performance stability and consequently the group decreases. To solve such problems, this study uses horizontal, vertical, and oblique pair comparisons, the algorithm being determined by several criteria through an incomplete linguistic custom relationship model [16]. Multiple decision-making criteria can meet the requirement.…”

Section: Multi-criteria Decision Makingmentioning

confidence: 99%

Understanding MCDM Preference Relations Index Method and Its Application

2022

jbab

View full text Add to dashboard Cite

Custom table (PSI) method. Priority selection coding was developed by Mania & Butt (2010) to solve MCDM problems. As proposed, it is not necessary to assign comparative importance between attributes. Choosing a desirable machine is an important concern for the manufacturing company. The selection process has some important selection properties and the task of this process is to select the preferred machine from among the multiple candidate machines. The problem of machine selection is a problem that is determined by many characters. This paper solves the problem of machine selection, which generates an optional selection code in a Flexible production cell. A case study is used to demonstrate that the proposed method is effective and feasible. This article explores the use of the MCDM System of Choice (PSI) method to address various decision-making issues commonly encountered during the design phase of a production system life cycle. To demonstrate the feasibility, applicability, and accuracy of the PSI method in solving the decision-making problem at the design stage of the product life cycle, five examples are cited from the literature and compared with the results obtained by past researchers. Research has concluded that the BSI method is logical and highly relevant to material selection issues. The choice of marketing area is an important factor in sales activities. Many factors are required in choosing a marketing area, including rental prices, area, audience, and distance. For a decision to select this marketing area to be effective, the hotel needs a decision support system that can provide the best possible service to guests and deliver the right decision in implementing alternatives, as there are responsibilities and responsibilities of many departments

show abstract

Section: Multi-criteria Decision Makingmentioning

confidence: 99%

Understanding MCDM Preference Relations Index Method and Its Application

2022

jbab

View full text Add to dashboard Cite

show abstract

“…Traditional approaches are based on statistical or rule‐based methods 7 to detect network anomalies and do not effectively handle complex and dynamic network traffic. In this case, network intrusion detection systems have played a paramount role in protecting computer networks, detecting and preventing unauthorized access, malicious attacks, data breaches, and potential cyber threats within computer networks in real time 4,5,8,9 . In addition, NIDS is one of the crucial components of comprehensive network security.…”

Section: Introductionmentioning

confidence: 99%

“…Furthermore, the NIDS is associated with cloud computing, which is challenging to secure from malicious actions by attackers 12 . Thus, ensuring cloud information using an effective intrusion detection system is essential 9 . Nevertheless, the traditional approaches like firewalls, anti‐viruses, and encryption‐decryption methods 5,13 are insufficient to catch the complex denial of service attacks (DoS) 9,14 and distributed denial of service attacks (DDoS) 13 .…”

Section: Introductionmentioning

confidence: 99%

“…In this case, network intrusion detection systems have played a paramount role in protecting computer networks, detecting and preventing unauthorized access, malicious attacks, data breaches, and potential cyber threats within computer networks in real time. 4,5,8,9 In addition, NIDS is one of the crucial components of comprehensive network security. The primary aim of the NIDS approach is to detect unauthorized and suspicious activities that can show intrusion behavior.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

An LSTM‐based novel near‐real‐time multiclass network intrusion detection system for complex cloud environments

Vibhute,

Khan,

Kanade

et al. 2024

Concurrency and Computation

View full text Add to dashboard Cite

SummaryThe Internet is connected with everyone for sharing and monitoring digital information. However, securing network resources from malicious activities is critical for several applications. Numerous studies have recently used deep learning‐based models in detecting intrusions and received relatively robust recognition outcomes. Nevertheless, most investigations have operated old datasets, so they could not detect the most delinquent attack information. Therefore, the current research proposes the long short‐term memory (LSTM)‐based near real‐time multiclass network intrusion detection system (NIDS) utilizing complex cloud CSE‐CICIDSS2018 datasets to secure and detect the network anomalous. The proposed strategy utilizes a random forest algorithm for dimensionality reduction and feature selection. In addition, the selected best suitable features were used in a deep learning‐based LSTM model developed for detecting network intrusions. The experimental outcomes reveal that the presented LSTM model obtained 99.66% testing accuracy with 0.12% loss. Thus, the suggested approach can detect network intrusions with the highest precision and lowest rate over the earlier designs.

show abstract

“…The second part is cloud's backend, which is made up of multiple servers and is the cloud itself. The second defence layer of a system includes intrusion detection systems (IDS).IDSs can discern between lawful and unlawful conduct using patterns of good traffic, typical behaviour, or particular rules that describe an assault.In contrast to conventional IDSs that might not be as successful against contemporary sophisticated cyberattacks, data mining, which is utilized to describe knowledge discovery, can help implement as well as deploy IDSs with higher accuracy as well as robust behaviour.Reliable datasets that I contain both benign and many attacks, (ii) meet real-world requirements, and (iii) are publically available are required in order to verify the effectiveness of such techniques [5].As first line of protection for computer security, the conventional preventative measures such user authentication, data encryption, avoiding programming errors, and firewalls are used. User authentication cannot stop illegal use in the case that a password is weak and hacked.Firewalls are susceptible to configuration mistakes and unclear or undefinable security policies.…”

Section: Introductionmentioning

confidence: 99%

Soft computing in computer network security protection system with machine learning based on level protection in the cloud environment

Thomas

Gupta

Rajan

et al. 2023

Preprint

View full text Add to dashboard Cite

Artificial neural networks (ANN), fuzzy inference systems, approximate reasoning, and derivative-free optimization approaches like evolutionary computation, among others, are all components of Soft Computing (SC), an innovative method for building computationally intelligent methods. Due to its widespread use and benefits, cloud computing is currently a major focus for researchers. The distributed nature of cloud computing and its complete reliance on the internet for service provision present security challenges, the most serious of which is insider Distributed Denial of Service (DDoS), which results in complete deactivation of services. Based on machine learning and the cloud, this study proposes a novel method for improving computing network security. Using a trust-based secure cloud environment and the Kernel principal component encoder architecture, the network monitoring is carried out. The soft computing environment-based detection of a cyberattack on the network is the purpose for the security enhancement. Throughput, QoS, latency, and packet delivery ratio for various monitored cyber security datasets are the focus of the experimental analysis.the proposed technique attainednetwork security analysis of 89%, throughput of 98%, QoS of 66%, latencyof 59%, packet delivery ratio of 83%.

show abstract

RETRACTED: An intrusion identification and prevention for cloud computing: From the perspective of deep learning

Cited by 30 publications

References 26 publications

Understanding MCDM Preference Relations Index Method and Its Application

Understanding MCDM Preference Relations Index Method and Its Application

An LSTM‐based novel near‐real‐time multiclass network intrusion detection system for complex cloud environments

Soft computing in computer network security protection system with machine learning based on level protection in the cloud environment

Contact Info

Product

Resources

About