Ja'far Alqatawna

Optimizing Feedforward neural networks using Krill Herd algorithm for E-mail spam detection

Krill Herd is a new optimization technique that was inspired by the herding behavior of real small crustaceans called Krills. The method was developed for continuous optimization problems and has recently been successfully applied to different complex problems. Feedforward neural network has a number of characteristics which make it suitable for solving complex classification problems. The training of the this type of neural networks is considered the most challenging operation. Training neural networks aims to find a nearly global optimal set of connection weights in a relatively short time. In this paper we propose an application of Krill Herd algorithm for training the Feedforward neural network and optimizing its connection weights. The developed neural network will be applied for an E-mail spam detection model. The model will be evaluated and compared to other two popular training algorithms; the Back-propagation algorithm and the Genetic Algorithm. Evaluation results show that the developed training approach using Krill Herd algorithm outperforms the other two algorithms.

Iris recognition system for secure authentication based on texture and shape features

One of the most accurate biometric authentication methods is iris pattern. It has the advantages of being stable, contactless and no users previous knowledge is required. This paper presents an iris recognition system for user authentication. To design the proposed iris authentication system we reviewed and evaluated four iris pattern recognition features including Histogram of Oriented Gradients (HOG), combined Gabor and Discrete Cosine Transform (DCT), and Grey level Co-occurrence Matrix (GLCM). The system was tested using UBIRIS.v1 IRIS dataset and the results showed that GLCM gives the largest Euclidean distance between two iris images for two different users, which is higher than using combined features. Moreover, GLCM gives the highest recognition accuracy using Logistic Model Trees (LMT) classifier. Accordingly, GLCM is regarded the most discriminative and the most effective technique for the proposed iris authentication system.

Online Social Networks Security: Threats, Attacks, and Future Directions

A list of well-known Online Social Networks extend to hundreds of available sites with hundreds of thousands, millions, and even billions of registered accounts; for instance, Facebook as of April 2016 has around two billion active users. Online Social Networks made a difference in many people’s lives and helped in opening avenues that were not possible before. However, as in any success story there is a downside. Cyber-attacks that used to have a small or limited effect can now have a huge distributed effect through utilizing those social network sites. Some attacks are more apparent than others in this context; hence this chapter discusses how serious attacks are possible in online social networks and what has been done to encounter them. It will discuss privacy, Sybil attacks, social engineering, spam, malware, botnet attacks, and the trade-off between services, security, and users’ rights.

Spam profile detection in social networks based on public features

In the context of Online Social Networks, Spam profiles are not just a source of unwanted ads, but a serious security threat used by online criminals and terrorists for various malicious purposes. Recently, such criminals were able to steal a number of accounts that belong to NatWest banks customers. Their attack vector was based on spam tweets posted by a Twitter account which looked very close to NatWest customer support account and leaded users to a link of a phishing site. In this study, we investigate the nature of spam profiles in Twitter with a goal to improve social spam detection. Based on a set of publicly available features, we develop spam profiles detection models. At this stage, a dataset of 82 Twitters profiles are collected and analyzed. With feature engineering, we investigate ten binary and simple features that can be used to classify spam profiles. Moreover, a feature selection process is utilized to identify the most influencing features in the process of detecting spam profiles. For feature selection, two methods are used ReliefF and Information Gain. While for classification, four classification algorithms are applied and compared: Decision Trees, Multilayer Perceptron, k-Nearest neighbors and Naive Bayes. Preliminary experiments in this work show that the promising detection rates can be obtained using such features regardless of the language of the tweets.

Risk adaptive hybrid RFID access control system

Dynamic environments pose a challenge for traditional access control models where permissions are granted or revoked merely based on predefined and static access policies making them incapable of dynamically adapting to changing conditions. Risk adaptive access control models have been gaining more attention in the research community as an alternative approach to overcome the limitations of traditional access control models. Radio Frequency Identification RFID is an emerging technology widely utilized in both physical and logical access control systems because of its contactless nature, low cost, high read/write speed and long distance operation. Serverless RFID system architecture offers better availability assurance and lower implementation cost, while access rights management is easier in server-based architecture. In this study, we continue to build on our previous research on the privacy and security of RFID access control systems without a backend database in order to overcome its limitations. We propose a hybrid design for a risk adaptive RFID access control system; that is, dynamically alternating between two access control modes, online server-based and offline serverless, to adapt to the level of risk depending on rule-based risk scenarios and current risk value. The proposed design combines features of both serverless and risk adaptive access control systems. Copyright

Road scene analysis for determination of road traffic density

Road traffic density has always been a concern in large cities around the world, and many approaches were developed to assist in solving congestions related to slow traffic flow. This work proposes a congestion rate estimation approach that relies on real-time video scenes of road traffic, and was implemented and evaluated on eight different hotspots covering 33 different urban roads. The approach relies on road scene morphology for estimation of vehicles average speed along with measuring the overall video scenes randomness acting as a frame texture analysis indicator. Experimental results shows the feasibility of the proposed approach in reliably estimating traffic density and in providing an early warning to drivers on road conditions, thereby mitigating the negative effect of slow traffic flow on their daily lives.

The State of Play in Jordanian E-government Services

This paper presents the major Information and Communication Technology (ICT) initiatives that have been taking place in Jordan and their effect in creating and promoting an e-culture within the Jordanian society. This is followed by an analysis of the Jordanian public e-services’ state of play using a previously proposed conceptual framework, the 6I maturity model, as a benchmark to gauge the maturity stage of these e-services, and to assess their perceptual effectiveness. This analysis is a part of a major field study which explores the perceptions of users’ and providers’ of the Jordanian public e-services. Overall, this paper concludes that most of the public e-services in Jordan are still in an early stage, and with the exception of a very few e-services, most of them have not obtained many of the expected outcomes that the rhetoric of national strategies has promised. Moreover, the study has confirmed through empirical investigation using the 6I maturity model that eservices do not necessarily evolve in stages of maturity as suggested by traditional maturity models.

Evolving Support Vector Machines using Whale Optimization Algorithm for spam profiles detection on online social networks in different lingual contexts

A new classification approach based Support Vector Machine is proposed for detecting spammers on Twitter.The proposed approach reveals the most influencing features in the process of identifying spammers.Different lingual contexts are studied: Arabic, English, Spanish, and Korean. Detecting spam profiles is considered as one of the most challenging issues in online social networks. The reason is that these profiles are not just a source for unwanted or bad advertisements, but could be a serious threat; as they could initiate malicious activities against other users. Realizing this threat, there is an incremental need for accurate and efficient spam detection models for online social networks. In this paper, a hybrid machine learning model based on Support Vector Machines and one of the recent metaheuristic algorithms called Whale Optimization Algorithm is proposed for the task of identifying spammers in online social networks. The proposed model performs automatic detection of spammers and gives an insight on the most influencing features during the detection process. Moreover, the model is applied and tested on different lingual datasets, where four datasets are collected from Twitter in four languages: Arabic, English, Spanish, and Korean. The experiments and results show that the proposed model outperforms many other algorithms in terms of accuracy, and provides very challenging results in terms of precision, recall, f-measure and AUC. While it also helps in identifying the most influencing features in the detection process.

Social Media Shaping e-Publishing and Academia

This book presents the current state of the art in the field of e-publishing and social media, particularly in the Arabic context. The book discusses trends and challenges in the field of e-publishing, along with their implications for academic publishing, information services, e-learning and other areas where electronic publishing is essential. In particular, it addresses (1) Applications of Social Media in Libraries and Information Centers, (2) Use of Social Media and E-publishing in E-learning (3) Information Retrieval in Social Media, and (4) Information Security in Social Media.

Analyzing CyberCrimes Strategies: The Case of Phishing Attack

The growth in technology usage came along with many risks and increase in cybercrimes incidents. Phishing attacks are a form of cybercrimes by which attackers trick victims in order to obtain personal and sensitive information. Phishers motivations include gaining unauthorized information and access, cause financial loss and many more negative impacts. While cybercriminals keep developing their techniques, investigating different attack styles and methodologies are important steps toward developing effective protection mechanisms. This paper contributes to this direction by presenting and analyzing various phishing attack styles including Nigerian, Ghanaian, Chinese and Russian cybercrime styles. Due to richness of learning resources Russians and Chinese were found to be using more advanced techniques than Ghanaians and Nigerians who has limited resources.