The continuous development and usage of multi-media-based applications and services have contributed to the exponential growth of social multimedia traffic. In this context, secure transmission of data plays a critical role in realizing all of the key requirements of social multimedia networks such as reliability, scalability, quality of information, and quality of service (QoS). Thus, a trust-based paradigm for multimedia analytics is highly desired to meet the increasing user requirements and deliver more timely and actionable insights. In this regard, software-defined networks (SDNs) play a vital role; however, several factors such as as-runtime security, and energy-aware networking limit its capabilities to facilitate efficient network control and management. Thus, with the view to enhance the reliability of the SDN, a hybrid deep-learning-based anomaly detection scheme for suspicious flow detection in the context of social multimedia is proposed. It consists of the following two modules: 1) an anomaly detection module that leverages improved restricted Boltzmann machine and gradient descent-based support vector machine to detect the abnormal activities, and 2) an end-to-end data delivery module to satisfy strict QoS requirements of the SDN, that is, high bandwidth and low latency. Finally, the proposed scheme has been experimentally evaluated on both real-time and benchmark datasets to prove its effectiveness and efficiency in terms of anomaly detection and data delivery essential for social multimedia. Further, a large-scale analysis over a Carnegie Mellon University (CMU)-based insider threat dataset has been conducted to identify its performance in terms of detecting malicious events such as-Identity theft, profile cloning, confidential data collection, etc.

Hybrid Deep-Learning-Based Anomaly Detection Scheme for Suspicious Flow Detection in SDN: A Social Multimedia Perspective

On cloud security requirements, threats, vulnerabilities and countermeasures: A survey

In recent years, the increased use of wireless networks for the transmission of large volumes of information has generated a myriad of security threats and privacy concerns; consequently, there has been the development of a number of preventive and protective measures including intrusion detection systems (IDS). Intrusion detection mechanisms play a pivotal role in securing computer and network systems; however, for various IDS, the performance remains a major issue. Moreover, the accuracy of existing methodologies for IDS using machine learning is heavily affected when the feature space grows. In this paper, we propose a IDS based on deep learning using feed forward deep neural networks (FFDNNs) coupled with a filter-based feature selection algorithm. The FFDNN-IDS is evaluated using the well-known NSL-knowledge discovery and data mining (NSL-KDD) dataset and it is compared to the following existing machine learning methods: support vectors machines, decision tree, K-Nearest Neighbor, and Naive Bayes. The experimental results prove that the FFDNN-IDS achieves an increase in accuracy in comparison to other methods.

/pdf/a-deep-learning-method-with-filter-based-feature-engineering-4fpo8vj0pi.pdf

A Deep Learning Method With Filter Based Feature Engineering for Wireless Intrusion Detection System

Intelligent approach to build a Deep Neural Network based IDS for cloud environment using combination of machine learning algorithms

Internet of Things (IoT) is widely accepted technology in both industrial as well as academic field. The objective of IoT is to combine the physical environment with the cyber world and create one big intelligent network. This technology has been applied to various application domains such as developing smart home, smart cities, healthcare applications, wireless sensor networks, cloud environment, enterprise network, web applications, and smart grid technologies. These wide emerging applications in variety of domains raise many security issues such as protecting devices and network, attacks in IoT networks, and managing resource-constrained IoT networks. To address the scalability and resource-constrained security issues, many security solutions have been proposed for IoT such as web application firewalls and intrusion detection systems. In this paper, a comprehensive survey on Intrusion Detection System (IDS) for IoT is presented for years 2015–2019. We have discussed various IDS placement strategies and IDS analysis strategies in IoT architecture. The paper discusses various intrusions in IoT, along with Machine Learning (ML) and Deep Learning (DL) techniques for detecting attacks in IoT networks. The paper also discusses security issues and challenges in IoT.

A Review on Machine Learning and Deep Learning Perspectives of IDS for IoT: Recent Updates, Security Issues, and Challenges

A novel architecture combined with optimal parameters for back propagation neural networks applied to anomaly network intrusion detection

Cloud computing is a newly emerged technology, and the rapidly growing field of IT. It is used extensively to deliver Computing, data Storage services and other resources remotely over internet on a pay per usage model. Nowadays, it is the preferred choice of every IT organization because it extends its ability to meet the computing demands of its everyday operations, while providing scalability, mobility and flexibility with a low cost. However, the security and privacy is a major hurdle in its success and its wide adoption by organizations, and the reason that Chief Information Officers (CIOs) hesitate to move the data and applications from premises of organizations to the cloud. In fact, due to the distributed and open nature of the cloud, resources, applications, and data are vulnerable to intruders. Intrusion Detection System (IDS) has become the most commonly used component of computer system security and compliance practices that defends network accessible Cloud resources and services from various kinds of threats and attacks. This paper presents an overview of different intrusions in cloud, various detection techniques used by IDS and the types of Cloud Computing based IDS. Then, we analyze some pertinent existing cloud based intrusion detection systems with respect to their various types, positioning, detection time and data source. The analysis also gives strengths of each system, and limitations, in order to evaluate whether they carry out the security requirements of cloud computing environment or not. We highlight the deployment of IDS that uses multiple detection approaches to deal with security challenges in cloud.

A survey of intrusion detection systems for cloud computing environment

In this paper we are proposing an adaptive and real-time approach to resolve real-time financial data integration latency problems and semantic heterogeneity. Due to constraints that we have faced in some projects that requires real-time massive financial data integration and analysis, we decided to follow a new approach by combining a hybrid financial ontology, resilient distributed datasets and real-time discretized stream. We create a real-time data integration pipeline to avoid all problems of classic Extract-Transform-Load tools, which are data processing latency, functional miscomprehensions and metadata heterogeneity. This approach is considered as contribution to enhance reporting quality and availability in short time frames, the reason of the use of Apache Spark. We studied Extract-Transform-Load (ETL) concepts, data warehousing fundamentals, big data processing technics and oriented containers clustering architecture, in order to replace the classic data integration and analysis process by our new concept resilient distributed DataStream for online analytical process (RDD4OLAP) cubes which are consumed by using Spark SQL or Spark Core basics.

/pdf/an-adaptive-and-real-time-based-architecture-for-financial-3lszhvcdiw.pdf

An adaptive and real-time based architecture for financial data integration

Diversity and heterogeneity are one of the key aspects of big data. Including both structured and also unstructured data. Understanding and making sense of the huge amount of data requires better approaches for deduction and novel learning systems to address the different difficulties in many domains of application, especially in transportation. Autonomous cars are the future of transportation, in this paper, we will discuss the best combination with big data; text analytics, image processing and big data sensors, from unstructured data and then we will showcase how this fusion of data gathered by different sources can improve reliability and efficiency in self-driving and, may lead us to rethink a new theories and models altogether, and finally develop a behavior vehicle, Capable, like a human, to develop a better understanding from perception and intuition.

From Big Data to Better Behavior in Self-Driving Cars

In this paper we present a new Golang based framework for distributed intensive data processing and also micro batching. It uses a novel approach, the persistent distributed channels, based on the concept of Share memory by communicating, and inspired from Resilient distributed datasets of Apache Spark. The architecture of our proposed system is considered as near-metal platform for Big Data operations in order to enhance the speed of massive data processing.

Noureddine Abghour

Papers

A novel architecture combined with optimal parameters for back propagation neural networks applied to anomaly network intrusion detection

A survey of intrusion detection systems for cloud computing environment

An adaptive and real-time based architecture for financial data integration

From Big Data to Better Behavior in Self-Driving Cars

A Near Metal Platform for Intensive Big Data Processing Using A Novel Approach: Persistent Distributed Channels