Search

It is critical to secure the Industrial Internet of Things (IIoT) devices because of potentially devastating consequences in case of an attack. Machine learning (ML) and big data analytics are the two powerful leverages for analyzing and securing the Internet of Things (IoT) technology. By extension, these techniques can help improve the security of the IIoT systems as well. In this paper, we first present common IIoT protocols and their associated vulnerabilities. Then, we run a cyber-vulnerability assessment and discuss the utilization of ML in countering these susceptibilities. Following that, a literature review of the available intrusion detection solutions using ML models is presented. Finally, we discuss our case study, which includes details of a real-world testbed that we have built to conduct cyber-attacks and to design an intrusion detection system (IDS). We deploy backdoor, command injection, and Structured Query Language (SQL) injection attacks against the system and demonstrate how a ML-based anomaly detection system can perform well in detecting these attacks. We have evaluated the performance through representative metrics to have a fair point of view on the effectiveness of the methods. - 2014 IEEE. Manuscript received January 16, 2019; revised April 1, 2019 and April 12, 2019; accepted April 13, 2019. Date of publication April 18, 2019; date of current version July 31, 2019. This work was supported by NPRP through the Qatar National Research Fund (a member of Qatar Foundation) under Grant NPRP 10-901-2-370. The work of M. A. Teixeira was supported in part by the São Paulo Research Foundation (FAPESP) under Grant 2017/01055-4 and in part by the Instituto Federal de Educação, Ciência e Tecnologia de São Paulo. (Corresponding author: Maede Zolanvari.) Scopus

Carriers network services are distributed, dynamic, and investment intensive. Deploying them as virtual network services (VNS) brings the promise of low-cost agile deployments, which reduce time to market new services. If these virtual services are hosted dynamically over multiple clouds, greater flexibility in optimizing performance and cost can be achieved. On the flip side, when orchestrated over multiple clouds, the stringent performance norms for carrier services become difficult to meet, necessitating novel and innovative placement strategies. In selecting the appropriate combination of clouds for placement, it is important to look ahead and visualize the environment that will exist at the time a virtual network service is actually activated. This serves multiple purposes clouds can be selected to optimize the cost, the chosen performance parameters can be kept within the defined limits, and the speed of placement can be increased. In this paper, we propose the P-ART (Predictive-Adaptive Real Time) framework that relies on predictive-deductive features to achieve these objectives. With so much riding on predictions, we include in our framework a novel concept-drift compensation technique to make the predictions closer to reality by taking care of long-term traffic variations. At the same time, near real-time update of the prediction models takes care of sudden short-term variations. These predictions are then used by a new randomized placement heuristic that carries out a fast cloud selection using a least-cost latency-constrained policy. An empirical analysis carried out using datasets from a queuing-theoretic model and also through implementation on CloudLab, proves the effectiveness of the P-ART framework. The placement system works fast, placing thousands of functions in a sub-minute time frame with a high acceptance ratio, making it suitable for dynamic placement. We expect the framework to be an important step in making the deployment of carrier-grade VNS on multi-cloud systems, using network function virtualization (NFV), a reality. This publication was made possible by NPRP grant # 8-634-1-131 from the Qatar National Research Fund (a member of Qatar Foundation), National Science Foundation, USA � CNS-1718929 and National Science Foundation, USA � CNS-1547380 . Scopus

The costs of delivering critical services, such as healthcare, power, financial systems and transportation are spiraling up while the performance expectations of them have risen manifold. The mechanics of providing these services (e.g., activities like processing satellite imagery for defense and civil applications, analyzing patient data for diagnosing acute ailments, ensuring uneventful working of unmanned vehicles and big data analytics for sustaining smart cities) all require unprecedented data acquisition, storage, computation and communication. Driven by the need to achieve agility, intelligence and high performance at lower cost and improve outcomes, these systems are increasingly relying on advanced methods and technologies. Trends show the prevalence of IoT for data collection, multi-cloud computing for storage and analytics and virtualization of communication components. The increasing sophistication of technology also increases susceptibility of these systems to cyberattacks. The overarching objective of the work presented in this paper is to show the feasibility and usefulness of AI-based hierarchical sparse deep neural network models for providing security to data in motion. The novelty of the work lies in the use of variable complexity models across multiple clouds and their synergistic training to reduce training time and improve detection accuracy for unknown attacks.

Network slicing in 5G is expected to essentially change the way in which network operators deploy and manage vertical services with different performance requirements. Efficient and secure slice provisioning algorithms are important since network slices share the limited resources of the physical network. In this article, we first analyze the security issues in network slicing and formulate an Integer Linear Programming (ILP) model for secure 5G core network slice provisioning. Then, we propose a heuristic 5G core network slice provisioning algorithm called VIKOR-CNSP based on VIKOR, which is a multi-criteria decision making (MCDM) method. In the slice node provisioning stage, the node importance is ranked with the VIKOR approach by considering the node resource and topology attributes. The slice nodes are then provisioned according to the ranking results. In the slice link provisioning stage, the k shortest path algorithm is implemented to obtain the candidate physical paths for the slice link, and a strategy for selecting a candidate physical path is proposed to increase the slice acceptance ratio. The strategy first calculates the path factor Pf which is the product of the maximum link bandwidth utilization of the candidate physical path and its hop-count, and then chooses the candidate physical path with the smallest Pf to host the slice link. Extensive simulations show that the proposed algorithm can achieve the highest slice acceptance ratio and the largest provisioning revenue-to-cost ratio, satisfying the security constraints of 5G core network slice requests.

Service Function Chaining (SFC) is the problem of deploying various network service instances over geographically distributed data centers and providing inter-connectivity among them. The goal is to enable the network traffic to flow smoothly through the underlying network, resulting in an optimal quality of experience to the end-users. Proper chaining of network functions leads to optimal utilization of distributed resources. This has been a de-facto model in the telecom industry with network functions deployed over underlying hardware. Though this model has served the telecom industry well so far, it has been adapted mostly to suit the static behavior of network services and service demands due to the deployment of the services directly over physical resources. This results in network ossification with larger delays to the end-users, especially with the data-centric model in which the computational resources are moving closer to end users. A novel networking paradigm, Network Function Virtualization (NFV), meets the user demands dynamically and reduces operational expenses (OpEx) and capital expenditures (CapEx), by implementing network functions in the software layer known as virtual network functions (VNFs). VNFs are then interconnected to form a complete end-to-end service, also known as service function chains (SFCs). In this work, we study the problem of deploying service function chains over network function virtualized architecture. Specifically, we study virtual network function placement problem for the optimal SFC formation across geographically distributed clouds. We set up the problem of minimizing inter-cloud traffic and response time in a multi-cloud scenario as an ILP optimization problem, along with important constraints such as total deployment costs and service level agreements (SLAs). We consider link delays and computational delays in our model. The link queues are modeled as M/D/1 (single server/Poisson arrival/deterministic service times) and server queues as M/M/1 (single server/Poisson arrival/exponential service times) based on the statistical analysis. In addition, we present a novel affinity-based approach (ABA) to solve the problem for larger networks. We provide a performance comparison between the proposed heuristic and simple greedy approach (SGA) used in the state-of-the-art systems. Greedy approach has already been widely studied in the literature for the VM placement problem. Especially we compare our proposed heuristic with a greedy approach using first-fit decreasing (FFD) method. By observing the results, we conclude that the affinity-based approach for placing the service functions in the network produces better results compared against the simple greedy (FFD) approach in terms of both, total delays and total resource cost. We observe that with a little compromise (gap of less than 10% of the optimal) in the solution quality (total delays and cost), affinity-based heuristic can solve the larger problem more quickly than ILP. This work has been supported under the grant ID NPRP 6 - 901 - 2 - 370 for the project entitled "Middleware Architecture for Cloud Based Services Using Software Defined Networking (SDN)", which is funded by the Qatar National Research Fund (QNRF) and a grant from Huawei. H. Anthony Chan was supported by Huawei. The statements made herein are solely the responsibility of the authors. Scopus

Efficient provisioning of 5G network slices is a major challenge for 5G network slicing technology. Previous slice provisioning methods have only considered network resource attributes and ignored network topology attributes. These methods may result in a decrease in the slice acceptance ratio and the slice provisioning revenue. To address these issues, we propose a two-stage heuristic slice provisioning algorithm, called RT-CSP, for the 5G core network by jointly considering network resource attributes and topology attributes in this paper. The first stage of our method is called the slice node provisioning stage, in which we propose an approach to scoring and ranking nodes using network resource attributes (i.e., CPU capacity and bandwidth) and topology attributes (i.e., degree centrality and closeness centrality). Slice nodes are then provisioned according to the node ranking results. In the second stage, called the slice link provisioning stage, the k-shortest path algorithm is implemented to provision slice links. To further improve the performance of RT-CSP, we propose RT-CSP+, which uses our designed strategy, called minMaxBWUtilHops, to select the best physical path to host the slice link. The strategy minimizes the product of the maximum link bandwidth utilization of the candidate physical path and the number of hops in it to avoid creating bottlenecks in the physical path and reduce the bandwidth cost. Using extensive simulations, we compared our results with those of the state-of-the-art algorithms. The experimental results show that our algorithms increase slice acceptance ratio and improve the provisioning revenue-to-cost ratio.

Recently, leading research communities have been investigating the use of blockchains for Artificial Intelligence (AI) applications, where multiple participants, or agents, collaborate to make consensus decisions. To achieve this, the data in the blockchain storage have to be transformed into blockchain knowledge. We refer to these types of blockchains as knowledge-based blockchains. Knowledge-based blockchains are potentially useful in building efficient risk assessment applications. An earlier work introduced probabilistic blockchain which facilitates knowledge-based blockchains. This paper proposes an extension for the probabilistic blockchain concept. The design of a reputation management framework, suitable for such blockchains, is proposed. The framework has been developed to suit the requirements of a wide range of applications. In particular, we apply it to the detection of malicious nodes and reduce their effect on the probabilistic blockchains' consensus process. We evaluate the framework by comparing it to a baseline using several adversarial strategies. Further, we analyze the collaborative decisions with and without the malicious node detection. Both results show a sustainable performance, where the proposed work outperforms others and achieves excellent results.

Network slicing for 5G provides Network-as-a-Service (NaaS) for different use cases, allowing network operators to build multiple virtual networks on a shared infrastructure. With network slicing, service providers can deploy their applications and services flexibly and quickly to accommodate diverse services' specific requirements. As an emerging technology with a number of advantages, network slicing has raised many issues for the industry and academia alike. Here, the authors discuss this technology's background and propose a framework. They also discuss remaining challenges and future research directions. This publication was made possible by the NPRP award (NPRP 8-634-1-131) from the Qatar National Research Fund (a member of The Qatar Foundation), Huawei Technologies, and the China Scholarship Council (201506270075). The statements made herein are solely the responsibility of the authors. Scopus

Deployment of Network Function Virtualization (NFV) over multiple clouds accentuates its advantages like the flexibility of virtualization, proximity to customers and lower total cost of operation. However, NFV over multiple clouds has not yet attained the level of performance to be a viable replacement for traditional networks. One of the reasons is the absence of a standard based Fault, Configuration, Accounting, Performance and Security (FCAPS) framework for the virtual network services. In NFV, faults and performance issues can have complex geneses within virtual resources as well as virtual networks and cannot be effectively handled by traditional rule-based systems. To tackle the above problem, we propose a fault detection and localization model based on a combination of shallow and deep learning structures. Relatively simpler detection of 'fault' and 'no-fault' conditions or 'manifest' and 'impending' faults have been effectively shown to be handled by shallow machine learning structures like Support Vector Machine (SVM). Deeper structure, i.e. the stacked autoencoder has been found to be useful for a more complex localization function where a large amount of information needs to be worked through, in different layers, to get to the root cause of the problem. We provide evaluation results using a dataset adapted from logs of disruption in an operator's live network fault datasets available on Kaggle and another based on multivariate kernel density estimation and Markov sampling., Comment: E-preprint

Fault and performance management systems, in the traditional carrier networks, are based on rule-based diagnostics that correlate alarms and other markers to detect and localize faults and performance issues. As carriers move to Virtual Network Services, based on Network Function Virtualization and multi-cloud deployments, the traditional methods fail to deliver because of the intangibility of the constituent Virtual Network Functions and increased complexity of the resulting architecture. In this paper, we propose a framework, called HYPER-VINES, that interfaces with various management platforms involved to process markers through a system of shallow and deep machine learning models. It then detects and localizes manifested and impending fault and performance issues. Our experiments validate the functionality and feasibility of the framework in terms of accurate detection and localization of such issues and unambiguous prediction of impending issues. Simulations with real network fault datasets show the effectiveness of its architecture in large networks. Scopus

A blockchain provides a securedparadigm to achieve consensus using a distributed and peer-to-peer network in which no trusted central party is required. As a result, it has the potential to resolve many challenges that are faced with current centralized controllers in globally distributed applications. To date, the blockchain technology has been used for recording transactions and tracking objects in which multiple participants reach a consensus on whether a transaction is valid or not. This paper introduces the novel paradigm of probabilistic blockchains, an extension of the current blockchains that allows building efficient and distributed risk assessment and decision-making applications in which multiple untrusting parties collaborate but may not completely agree on the outcome. The paradigm is particularly useful for risk assessment, where a group of decision-makersneeds to decide or analyze an event based on imperfect information. The proposed approach can be used in applications like intrusion detections, stock market predictions, insurance, and recommendation systems. The paper presents and analyzes the application of probabilistic blockchains for intrusion detection systems for computer networks. The results show the feasibility and efficiency of the proposed paradigm in making such decisions.

Inguinal hernia with vermiform appendix as content is known as Amyand’s hernia. It is a rare entity but we encountered four cases within six months. A 52-year-old female had high grade fever and evidence of inflammatory pathology involving the ileocaecal region. She was initially managed conservatively and subsequently underwent exploratory laparatomy. The appendix was perforated and herniating in the inguinal canal. Appendectomy was done with herniorrhaphy without mesh placement. A 74-year-old male with bilateral inguinal hernia, of which, the right side was more symptomatic, underwent open exploration. Operative findings revealed a lipoma of the sac and a normal appearing appendix as content. Contents were reduced without appendectomy and mesh hernioplasty was performed. A 63-year-old male with an obstructed right sided hernia underwent emergency inguinal exploration which revealed edematous caecum and appendix as content without any inflammation. Contents were reduced without any resection. Herniorrhaphy was performed without mesh placement. A 66-year-old male with an uncomplicated right inguinal hernia underwent elective surgery. The sac revealed an appendix with adhesions at the neck. Contents were reduced after adhesiolysis and hernioplasty was performed with mesh placement. Emphasis is made to the rarity of disease, variation in presentation, and difference in treatment modalities depending upon the state of appendix.

Lately application service providers (ASPs) and Internet service providers (ISPs) are being confronted with the unprecedented challenge of accommodating increasing service and traffic demands from their geographically distributed users. Many ASPs and ISPs, such as Facebook, Netflix, AT&T and others have adopted micro-service architecture to tackle this problem. Instead of building a single, monolithic application, the idea is to split the application into a set of smaller, interconnected services, called micro-services (or simply services). Such services are lightweight and perform distinct tasks independent of each other. Hence, they can be deployed quickly and independently as user demands vary. Nevertheless, scheduling of micro-services is a complex task and is currently under-researched. In this work, we address the problem of scheduling micro-services across multiple clouds, including micro-clouds. We consider different user-level SLAs, such as latency and cost, while scheduling such services. Our aim is to reduce overall turnaround time for the complete end-to-end service in service function chains and reduce the total traffic generated. In this work we present a novel fair weighted affinity-based scheduling heuristic to solve this problem. We also compare the results of proposed solution with standard biased greedy scheduling algorithms presented in the literature and observe significant improvements. This publication was made possible by the NPRP award [NPRP 6-901-2-370] from the Qatar National Research Fund (a member of The Qatar Foundation) and Huawei Technologies. The statements made herein are solely the responsibility of the author[s]. References [1] L. Sorensen and K. E. Skouby, "User Scenarios 2020 - a worldwide wireless future report," WWRF, July 2009. Scopus

Carriers find Network Function Virtualization (NFV) and multi-cloud computing a potent combination for deploying their network services. The resulting virtual network services (VNS) offer great flexibility and cost advantages to them. However, vesting such services with a level of performance and availability akin to traditional networks has proved to be a difficult problem for academics and practitioners alike. There are a number of reasons for this complexity. The challenging nature of management of fault and performance issues of NFV and multi-cloud based VNSs is an important reason. Rule-based techniques that are used in the traditional physical networks do not work well in the virtual environments. Fortunately, machine and deep learning techniques of Artificial Intelligence (AI) are proving to be effective in this scenario. The main objective of this tutorial is to understand how AI-based techniques can help in fault detection and localization to take such services closer to the performance and availability of the traditional networks. A case study, based on our work in this area, has been included for a better understanding of the concepts. - 2019 This publication was made possible by NPRP grant #8-634-1-131 from the Qatar National Research Fund (a member of Qatar Foundation), NSF grants CNS-1718929and CNS-1547380.The statements made herein are solely the responsibility of the authors.This paper draws from earlier works of the authors including ̳HYPER-VINES: A Hybrid Learning Fault and Performance Issues Eradicator for Virtual Network Services over Multi-Cloud Systems’ presented at the IEEE ICNC 2019 Conference in February 2019, andfrom the other references listed in the reference section. Scopus

Network function virtualization (NFV) over multi-cloud promises network service providers amazing flexibility in service deployment and optimizing cost. Telecommunications applications are, however, sensitive to performance indicators, especially latency, which tend to get degraded by both the virtualization and the multiple cloud requirement for widely distributed coverage. In this work we propose an efficient framework that uses the novel concept of random cloud selection combined with a support vector regression based predictive model for cost optimized latency aware placement (COLAP) of service function chains. Extensive empirical analysis has been carried out with training datasets generated using a queuing-theoretic model. The results show good generalization performance of the predictive algorithm. The proposed framework can place thousands of virtual network functions in less than a minute and has high acceptance ratio. Scopus

Application Service Providers (ASPs) may obtain resources from a number of cloud service providers (CSPs) in an attempt to improve latency and minimize operational expenses (OpEx). The CSPs may use management and control platforms, such as Open Stack and EC2 and the network service providers (NSPs) may use network management platforms, such as, Open Daylight. However, today the ASPs do not have a common management and control platform that would present to them a converged view of all the cloud and network resources. OpenADN being developed at Washington University in Saint Louis aims to allow the ASPs dynamic and real time control of virtual resources across multiple clouds and networks to provide efficient application delivery. The OpenADN platform itself is a complex distributed and multi-threaded system. Performance evaluation and assessment of need for optimization of such a complex platform requires precise and fine-grained behavioral data. In this paper we establish the need for profiling OpenADN like platforms so that the ASPs can optimize its behavior and control their cost, performance (latency) and energy consumption.

Transition to Next Generation Networks is likely to raise questions about how inter-operator interconnections should take place in a heterogeneous environment. The NGN architecture introduces several degrees of complexity, requiring decisions on issues like the layers and planes at which the interconnection among different service provider. domains should take place and how adequate quality of service can be ensured, over the interconnection, for various services. While intra-operator QoS in NGN is well researched and applied, inter-operator QoS is complex and still being discussed in academia, international standards bodies and industry. This paper proposes metrics for intra and inter domain QoS in a heterogeneous environment and tests it with actual data. It is seen that a combination of selected parameters from measurements taken from operational networks and operator reported data, show a strong correlation with the QoS reflected by consumer surveys.

Application Service Providers (ASPs) obtaining resources from multiple clouds have to contend with different management and control platforms employed by the cloud service providers (CSPs) and network service providers (NSP). Distributing applications on multiple clouds has a number of benefits but the absence of a common multi-cloud management platform that would allow ASPs dynamic and real-time control over resources across multiple clouds and interconnecting networks makes this task arduous. OpenADN, being developed at Washington University in Saint Louis, fills this gap. However, performance issues of such a complex, distributed and multi-threaded platform, not tackled appropriately, may neutralize some of the gains accruable to the ASPs. In this paper, we establish the need for and methods of collecting precise and fine-grained behavioral data of OpenADN like platforms that can be used to optimize their behavior in order to control operational cost, performance (e.g., latency) and energy consumption., Comment: E-preprint