Cloud Firewall Under Bursty and Correlated Data Traffic: A Theoretical Analysis

Carvalho, Glaucio H. S.; Woungang, Isaac; Anpalagan, Alagan

doi:10.1109/tcc.2020.3000674

Cited by 12 publications

(5 citation statements)

References 28 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Results demonstrating the effectiveness of the robust service mapping scheme in optimizing service allocation for multi-tenant clouds. [46] Theoretical analysis of cloud firewalls under bursty and correlated data traffic patterns, aiming to provide insights into their performance.…”

Section: Ref No Methodology Novelty Resultsmentioning

confidence: 99%

VMMISD: An Efficient Load Balancing Model for Virtual Machine Migrations via Fused Metaheuristics With Iterative Security Measures and Deep Learning Optimizations

Brahmam,

2024

IEEE Access

View full text Add to dashboard Cite

As cloud computing continues to evolve, the need for efficient and secure management of virtual machine (VM) migrations has become increasingly evident. Traditional models often fall short in optimizing load balancing and energy consumption while ensuring a high level of security. In this work, we propose the Load Balancing and Energy-Efficient Migration Model, an innovative approach that leverages bioinspired algorithms and advanced security measures to optimize VM migrations. The initial novelty of our model is the integration of Genetic Algorithms with Ant Colony Optimization for resource scheduling operations. These algorithms were specifically chosen for their proven effectiveness in solving complex optimization problems by simulating natural processes. Additionally, our model incorporates a Deep Reinforcement Learning-based Iterative-learning Contextual Side chaining Model to enhance security measures. This approach not only learns and adapts to new security threats over time but also utilizes contextual side-chaining to link related security events, thereby providing a robust defense mechanism against potential threats. The affinity between VMs and physical machines is quantified using K Means Clustering and Fuzzy Logic, which ensures optimal load balancing while accounting for the uncertainty inherent in the migration process. Furthermore, we employ Bidirectional Long Short-Term Memory networks with Recurrent Graph Neural Network, for accurate workload prediction and informed migration decision Making process. The selection of these techniques is grounded in their proven capability to analyze historical data and predict future trends with high accuracy levels. Our proposed model demonstrates marked improvements in several key performance metrics. We achieved a 4.5% reduction in makespan, a 4.9% increase in deadline hit ratio, and a 3.9% improvement in task diversity. Furthermore, computational complexity was reduced by 8.3%, VM migration efficiency improved by 2.5%, and the delay of computation was significantly reduced by 9.5%. Importantly, the integration of the Iterative-learning Contextual Side chaining Model significantly enhanced the security and quality of service (QoS) under attack scenarios, resulting in a 10.4% improvement in response speed, a 2.5% reduction in energy consumption during block mining, a 3.9% improvement in throughput, and an 8.5% reduction in storage costs. This Load Balancing and Energy-Efficient Migration Model represents a significant advancement in addressing the challenges of load balancing, energy efficiency, and security in VM migrations. Through the meticulous integration of bioinspired algorithms, advanced security measures, and machine learning techniques, our model provides a comprehensive and innovative solution that markedly improves system performance, reduces energy consumption, and fortifies security, thereby paving the way for a more efficient and secure cloud computing ecosystem.

show abstract

Section: Ref No Methodology Novelty Resultsmentioning

confidence: 99%

VMMISD: An Efficient Load Balancing Model for Virtual Machine Migrations via Fused Metaheuristics With Iterative Security Measures and Deep Learning Optimizations

Brahmam,

2024

IEEE Access

View full text Add to dashboard Cite

show abstract

“…Учитывая, что свойство самоподобия наблюдается в широких временных масштабах (например, при различном временном разрешении на уровне бит, пакетов, потоков и т.д. ), наличие в сигнале продолжительных атак и аномальной активности изменяет самоподобную природу трафика, приводит [4,[10][11], а также см. 9 Информация о различии ФР обрабатываемых процессов (если они доступны для обработки) при разном разрешении по времени может быть использована для модификации рассмотренных алгоритмов обнаружения/классификации КА и может привести к улучшению показателей классификации методами машинного обучения.…”

Section: постановка задачиunclassified

Classification of Computer Attacks Using Multifractal Spectrum of Fractal Dimension

2024

Cybersecurity Issues

View full text Add to dashboard Cite

Цель исследования: разработка метода повышения эффективности бинарной и многоклассовой классификации компьютерных атак (КА) путем использования дополнительных информативных признаков, в качестве которых предложно использовать мультифрактальный спектр фрактальной размерности (МСФР) обрабатываемых последовательностей.Методы исследования: дискретный вейвлет анализ, мультифрактальный анализ, машинное обучение, программная реализация комбинированного метода многоклассовой классификации в совокупности с методами фрактального анализа.Объектами исследования являются теоретические и практические вопросы разработки, реализации и визуализации алгоритмов обнаружения и классификации КА в целях информационной безопасности.Результаты исследования. Разработаны метод и алгоритм композиции машинного обучения и методов мультифрактального анализа обрабатываемых процессов с целью повышения эффективности многоклассовой классификации КА. Обоснованы границы изменения входных параметров алгоритма, для корректной многоклассовой классификации компьютерных атак. Показана целесообразность использования при классификации КА характеристик МСФР, что позволяет повысить эффективность классификации атак методами машинного обучения за счет расширения количества атрибутов параметрами МСФР.Практическая значимость: представленный метод является универсальным и может быть применен в различных системах обеспечения информационной безопасности.

show abstract

“…Denial of Service (DoS) attack has been one of the major threats to organizations worldwide. Recently, it has been shown that the scaling process of cloud computing is able to thwart the destruction power of a DoS attack [63]. However, the resource-constrained nature of edge computing exacerbates the risk of a successful DoS attack.…”

Section: Motivationmentioning

confidence: 99%

Security Risk-Aware Resource Management Mechanism for the 5G Cloudified Infrastructure

Carvalho

2024

Preprint

View full text Add to dashboard Cite

<p>5G wireless networks will play a critical role in society by providing ubiquitous access to end users, supporting mission critical applications, and interconnecting other critical infrastructure systems. Given its criticality, cybersecurity should be taken by design to ensure the security of running services and compliance with Service Level Agreements (SLA). This Thesis addresses the problem of security-aware resource allocation of the 5G cloudfied infrastructure aiming at minimizing the security risks while maximizing the dependability. To this end, a risk-aware edge-cloud mechanism in addition to three stochastic optimal controllers are proposed to efficiently manage the cloudified infrastructure to ensure the protection of services and applications as well as the protection of the infrastructure against cyber threats such as resource exhaustion due to flash network traffic, DoS attack, and SLA violations. To ensure a secure and SLA compliant operation of the cloudified 5G infrastructure, new and innovative cost structures are proposed to guide the optimal controllers towards a safe and sustainable operation where it is shown that they offset the cost of operationalizing the cloudified infrastructure by offering economical benefits related to the provisioning of secure and reliable services. Furthermore, we propose new security and dependability metrics that allows for the quantification of the perceived security risk of services, the probability of SLA violation, the probability of edge placement, the probability of cloud placement and the probability of a DoS attack. Considering the risk-awareness of the proposed mechanisms, they can be successfully integrated into the proposed agile security framework, which is based on an offensive posture that allows for a rapid response to cyber threats that might endanger the operations of the cloudified 5G infrastructure. Last but not least, this Thesis emphasizes the application of stochastic process and stochastic optimization which are essential tools to capture the uncertainties in dealing with the security aspects of the massive infrastructure, the demand and workload characterization.</p>

show abstract

Cloud Firewall Under Bursty and Correlated Data Traffic: A Theoretical Analysis

Cited by 12 publications

References 28 publications

VMMISD: An Efficient Load Balancing Model for Virtual Machine Migrations via Fused Metaheuristics With Iterative Security Measures and Deep Learning Optimizations

VMMISD: An Efficient Load Balancing Model for Virtual Machine Migrations via Fused Metaheuristics With Iterative Security Measures and Deep Learning Optimizations

Classification of Computer Attacks Using Multifractal Spectrum of Fractal Dimension

Security Risk-Aware Resource Management Mechanism for the 5G Cloudified Infrastructure

Contact Info

Product

Resources

About