While it is well understood that the emerging Social Internet of Things (SIoT) offers a description of a new world of billions of humans which are intelligently communicate and interact with each other. SIoT presents new challenges for suggesting useful objects with certain services for people. This is due to the limitation of social networks between human and objects, such as the evaluation of the various patterns inherent in human walk in cities. In this study we focus services on the problem of recommendation on SIoT which is very important for many applications such as urban computing, smart cities, and health care. The optimized results of swarm of certain infected people COViD-19 introduced in this paper aims at finding a given region of interest. Guided by a fitness function, the particle swarm optimization (PSO) algorithm has proved its efficiency to explore the search space and find the optimal solution. However, in real world scenarios in which the peoples are simulated as particles, there are practical constraints that should be taken into considerations. The most two significant constraints are (1) given the social-distance, the measurement of input variable fluctuations and their possibility of occurring via probability distribution function over the whole particles. (2) given the limited the communication range of particle/people/users, therefore, the spread of the diseases are simulated and evaluated using neighborhood particle swarm optimization (NPSO).

Network and Internet security is a critical universal issue. The increased rate of cyber terrorism has put national security under risk. In addition, Internet attacks have caused severe damages to different sectors (i.e., individuals, economy, enterprises, organizations and governments). Network Intrusion Detection Systems (NIDS) are one of the solutions against these attacks. However, NIDS always need to improve their performance in terms of increasing the accuracy and decreasing false alarms. Integrating feature selection with intrusion detection has shown to be a successful approach since feature selection can help in selecting the most informative features from the entire set of features. Usually, for the stealthy and low profile attacks (zero - day attacks), there are few neatly concealed packets distributed over a long period of time to mislead firewalls and NIDS. Besides, there are many features extracted from those packets, which may make some machine learning-based feature selection methods to suffer from overfitting especially when the data have large numbers of features and relatively small numbers of examples. In this paper, we are proposing a NIDS based on a feature selection method called Recursive Feature Addition (RFA) and bigram technique. The system has been designed, implemented and tested. We tested the model on the ISCX 2012 data set, which is one of the most well-known and recent data sets for intrusion detection purposes. Furthermore, we are proposing a bigram technique to encode payload string features into a useful representation that can be used in feature selection. In addition, we propose a new evaluation metric called (combined) that combines accuracy, detection rate and false alarm rate in a way that helps in comparing different systems and selecting the best among them. The designed feature selection-based system has shown a noticeable improvement on the performance using different metrics. (C) 2017 Elsevier Ltd. All rights reserved.

Nowadays, the Internet is experiencing many attacks of various kinds that put its information under risk. Therefore, information security is currently under real threat as a result of network attacks [40]. Therefore, to overcome the network attacks, intrusion detection systems (IDS) have been developed to detect attacks and notify network administrators [16]. The IDSs are now being studied widely to provide the defense-in-depth to network security framework. The IDSs are usually categorized into two types: anomaly detection and signature-based detection [40]. Anomaly detection utilizes a classifier that classifies the given data into normal and abnormal data [34]. Signature-based detection depends on an up-to-date database of known attacks’ signatures to detect the incoming attacks [40]. Network Intrusion Detection Systems (NIDS) are considered as classification problems and are also characterized by large amount of data and numbers of features [44]. In recent years, Internet users have suffered from many types of attacks. These cyber attacks are sometimes so damaging and cost billions of dollars every year [28]. Some of these attacks were able to access sensitive information and reveal credit cards numbers, delete entire domains, or even prevent legitimate users from being served by servers such as in the case of denial-of-service (DoS) attacks. The most common type of Internet attack is intrusion. These days, the most popular Internet services are being attacked by many intrusion attempts every day. Therefore,

This chapter discusses intrusion detection applications for two contemporary environments: mobile devices and cloud computing. The chapter starts by introducing the most well-known mobile device operating systems and cloud computing models. Next, the chapter discusses the risks to which these environments are exposed as a result of intrusions, and the sources and origins of attacks in both environments. Furthermore, classes of malware and types of attacks are explained. In addition, the chapter explores techniques employed by mobile malware as well as techniques employed by intrusions that infect cloud computing systems. The chapter also gives a variety of new examples of malware that infect mobile phones and intrusions into cloud computing systems. Moreover, the chapter discusses types of intrusion detection systems and explains performance metrics for evaluating intrusion detection systems in both environments.

The past several years have seen many new services spread across the Internet. One of the biggest trends has been social media services such as Facebook and Twitter. Although social media is the major trend, it is not the only one. Cloud computing has made a large impact on the computing industry in recent years. Whether being utilized to provide highly scalable robust environments for applications or just being used as a marketing ploy, one thing is certain: cloud computing has the potential to yet again change the way we interact with computer systems. There is just one major factor separating cloud computing from becoming widely accepted both personally and commercially and that is security. As cloud systems re-innovate ways of request distribution and load balancing, it is important to test these systems against attacks such as the denial of service attack. There is a strong emphasis on researching these attacks since cloud computing is re-inventing the payment systems in which consumers utilize resources. This paper examines the Google App Engine and its resilience to denial of service attacks. Further the paper demonstrates the strain such an attack has on the servers that facilitate the services and finally discuss the preventative measures set in place by Google and how they are only temporary solutions.

Feature selection is still a vital area for research in the machine learning field. After the emergence of big data, the need for mining large data sizes has increased to provide faster and more accurate predictions. Feature selection is concerned with selecting the most important features from a set of input features since some datasets may contain irrelevant and/or redundant features. In this paper, a new feature selection method of type embedded is presented and discussed with some preliminary results using existing benchmark datasets. The new method is called Recursive Feature Addition which works in a forward fashion and is based on Support Vector Machines. The new method has been applied to five different benchmark datasets and for which it has shown superior performance in terms of accuracy and time as compared to Filter, Wrapper and other Embedded methods.

Applying security to the transmitted medical images is important to protect the privacy of patients. Secure transmission requires cryptography, and watermarking to achieve confidentiality, and data integrity. Improving cryptography part needs to use an encryption algorithm that stands for a long time against different attacks. The proposed method is based on number theory and uses Chinese remainder theorem as a backbone. This approach achieves high level of security and stands against different attacks for a long time. On watermarking part, the medical image is divided into two regions: a region of interest (ROI) and a region of background (ROB). The pixel values of the ROI contain the important information so this region must not experience any change. The proposed watermarking technique is based on dividing the medical image in to blocks and inserting the watermark to the ROI by shifting the blocks. Then, an equivalent number of blocks in the ROB are removed. This approach can be considered as lossless since it does not affect on the ROI, also it does not increase the image size. In addition, it can stand against some watermarking attacks such cropping, and noise.