NFV-Based Scheme for Effective Protection against Bot Attacks in AI-Enabled IoT

Memos, Vasileios A.; Psannis, Kostas E.

doi:10.1109/iotm.001.2100175

Cited by 7 publications

(7 citation statements)

References 14 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Thanks to network softwarization, the application of Artificial Intelligence (AI) and Machine Learning (ML) to networking is easier to implement nowadays [8]. ML is a branch of AI that defines any computational method in which the results of previous events or decisions are used to improve predictions or decisions [36], allowing systems to improve themselves without being explicitly programmed.…”

Section: Machine Learning (Ml)mentioning

confidence: 99%

“…It also enables intelligent VNF management with consideration of system cost (mainly using DRL), which enables self-driven network service orchestration for complex large-scale IoT NFV-enabled networks [1] [4]. Security is a major concern in IoT networks, and as softwarization opens many attack vectors, the use of ML allows to counteract them [36]. As security VNFs are deployed in the IoT network, intelligence allows autonomous placement and orchestration, ensuring high adaptabil-25 ity to requirements that may vary, and thus ensuring the dynamism of VNF deployment [63].…”

Section: Intelligent Iot Network Softwarizationmentioning

confidence: 99%

“…In [36], the authors highlight the significant problem posed by the uncontrolled proliferation of insecure IoT-based devices. They outline the vulnerabilities associated with these devices and propose a solution using an NFV infrastructure in conjunction with emerging technologies to enable intelligent management and enhanced protection against botnet attacks.…”

mentioning

confidence: 99%

See 2 more Smart Citations

Review and analysis of recent advances in intelligent network softwarization for the Internet of Things

Zormati,

Lakhlef,

Ouni

2024

Computer Networks

View full text Add to dashboard Cite

Section: Machine Learning (Ml)mentioning

confidence: 99%

Section: Intelligent Iot Network Softwarizationmentioning

confidence: 99%

See 1 more Smart Citation

Review and analysis of recent advances in intelligent network softwarization for the Internet of Things

Zormati,

Lakhlef,

Ouni

2024

Computer Networks

View full text Add to dashboard Cite

“…6G is envisioned to support peak data rates as high as 1 Tbps, an E2E latency of less than 1 ms, the E2E network reliability to be near 99.99999%, and to have as many as 10 million connected devices per square kilometer to support Internetof-Everything (IoE). 6G is envisioned to support newer applications and use cases, a few of which are discussed as follows [8], [20], [21], [22], [23]:…”

Section: Introductionmentioning

confidence: 99%

Blockchain for Dynamic Spectrum Access and Network Slicing: A Review

et al. 2023

View full text Add to dashboard Cite

Dynamic spectrum access (DSA) and network slicing are some of the principal concepts to realize the emerging applications in Beyond 5th Generation (B5G) and 6th Generation (6G) networks. The frequency spectrum remains scarce and underutilized, while the performance requirements in terms of data throughput and latency of the network tenants have diversified. DSA allows for the efficient utilization of spectrum resources, while network slicing aims to serve network users with highly distinctive service needs. Lack of incentivization, sharing of spectrum resources among multiple operators, and lack of trust between operators are some of the challenges faced by centralized DSA approaches. Similarly, secure network slice orchestration, slice-isolation, secure access to network resources, privacy of user sensitive data, assuring the provision of Service Level Agreements (SLAs), are some of the challenges in existing network slicing techniques. Blockchain due to its innate capabilities can be a promising technology to solve the key issues pertaining to current DSA and network slicing approaches. Blockchain through smart contracts, provides traceability of network resources, auditability and accountability of network operators and service providers. Smart contracts facilitate the automation of resource sharing and network slice orchestration, while ensuring that SLAs are met, and network operators are compensated. This paper first provides a comprehensive overview of the DSA concept, the existing DSA techniques, and the challenges posed by these techniques. This is followed by a detailed description of network slicing, its key elements and architecture, various network slicing parameters, existing network slicing techniques and their challenges. Then an in-depth review on blockchain, its working principle, factors that affect blockchain implementation, and a comparison of various open-source blockchain platforms that support smart contracts is presented. This discussion is summarized by presenting the state-of-the-art in the blockchain-enabled DSA and network slicing, challenges and trade-offs of these techniques, and the gaps and future directions in this research area. Finally, we conclude by providing some future research directions.

show abstract

“…The IoT is a technology that is growing quickly, with fifty billion devices expected to be in use worldwide [ 4 , 5 ]. IoT devices have become easy targets for attackers because they do not have basic security protocols [ 6 , 7 ]. According to Statistica [ 8 , 9 ], 5200 attacks are launched against IoT devices monthly.…”

Section: Introductionmentioning

confidence: 99%

A novel hybrid optimization enabled robust CNN algorithm for an IoT network intrusion detection approach

et al. 2022

View full text Add to dashboard Cite

Due to the huge number of connected Internet of Things (IoT) devices within a network, denial of service and flooding attacks on networks are on the rise. IoT devices are disrupted and denied service because of these attacks. In this study, we proposed a novel hybrid meta-heuristic adaptive particle swarm optimization–whale optimizer algorithm (APSO-WOA) for optimization of the hyperparameters of a convolutional neural network (APSO-WOA-CNN). The APSO–WOA optimization algorithm’s fitness value is defined as the validation set’s cross-entropy loss function during CNN model training. In this study, we compare our optimization algorithm with other optimization algorithms, such as the APSO algorithm, for optimization of the hyperparameters of CNN. In model training, the APSO–WOA–CNN algorithm achieved the best performance compared to the FNN algorithm, which used manual parameter settings. We evaluated the APSO–WOA–CNN algorithm against APSO–CNN, SVM, and FNN. The simulation results suggest that APSO–WOA–CNf[N is effective and can reliably detect multi-type IoT network attacks. The results show that the APSO–WOA–CNN algorithm improves accuracy by 1.25%, average precision by 1%, the kappa coefficient by 11%, Hamming loss by 1.2%, and the Jaccard similarity coefficient by 2%, as compared to the APSO–CNN algorithm, and the APSO–CNN algorithm achieves the best performance, as compared to other algorithms.

show abstract

NFV-Based Scheme for Effective Protection against Bot Attacks in AI-Enabled IoT

Cited by 7 publications

References 14 publications

Review and analysis of recent advances in intelligent network softwarization for the Internet of Things

Review and analysis of recent advances in intelligent network softwarization for the Internet of Things

Blockchain for Dynamic Spectrum Access and Network Slicing: A Review

A novel hybrid optimization enabled robust CNN algorithm for an IoT network intrusion detection approach

Contact Info

Product

Resources

About