Search

Recently, phishing attacks have been a crucial threat to cyberspace security. Phishing is a form of fraud that attracts people and businesses to access malicious uniform resource locators (URLs) and submit their sensitive information such as passwords, credit card ids, and personal information. Enormous intelligent attacks are launched dynamically with the aim of tricking users into thinking they are accessing a reliable website or online application to acquire account information. Researchers in cyberspace are motivated to create intelligent models and offer secure services on the web as phishing grows more intelligent and malicious every day. In this paper, a novel URL phishing detection technique based on BERT feature extraction and a deep learning method is introduced. BERT was used to extract the URLs’ text from the Phishing Site Predict dataset. Then, the natural language processing (NLP) algorithm was applied to the unique data column and extracted a huge number of useful data features in terms of meaningful text information. Next, a deep convolutional neural network method was utilised to detect phishing URLs. It was used to constitute words or n-grams in order to extract higher-level features. Then, the data were classified into legitimate and phishing URLs. To evaluate the proposed method, a famous public phishing website URLs dataset was used, with a total of 549,346 entries. However, three scenarios were developed to compare the outcomes of the proposed method by using similar datasets. The feature extraction process depends on natural language processing techniques. The experiments showed that the proposed method had achieved 96.66% accuracy in the results, and then the obtained results were compared to other literature review works. The results showed that the proposed method was efficient and valid in detecting phishing websites’ URLs.

The assessment and evaluation of information system’s quality is vital and necessary. Health information system (HIS) is broadly spread and usage. Nowadays, HIS is attaining reputation importance and a boundless potential for developing countries. HIS has espoused by diversities healthcare providers to convey a qualified patient safety, patient healthcare services, efficient and effectiveness patient care, minimum medical faults, and patient satisfaction by gaining access to truthful information at anytime and anywhere. In KSA, many hospitals adopted HIS so it is becoming essential to evaluate the quality of these systems. This work implements Delone & McLean (D&M) quality model to evaluate the quality of HIS systems in Riyadh in order to sustain the quality of patient care and improve it if required. Delone & McLean quality model is the most validated and popular model used to qualify the factors of success of HIS system. The main objective is to assess the HIS placed in KSA hospitals, which leads to higher quality for patient healthcare. This study emphases on six interrelated measurements of IS success criteria that have been specified by the model. These measurement criteria are information quality, system quality, user satisfaction, services quality, use and net benefits. According to D&M model, these factors interrelated and has positively effect to each other. In this study, a questionnaire is disseminated to all possible stakeholders of HIS in four hospitals in Riyadh. The analysis of the results gathered from the questionnaire is conducted to validate the success of HIS and to recover the HIS Quality in KSA Hospital.

growth of intelligent intrusion and diverse attack techniques in network systems stimulate computer scientists and mathematical researchers to challenge the dangers of intelligent attacks. In this work, we integrate artificial immune algorithm with non-linear classification of pattern recognition and machine learning methods to solve the problem of intrusion detection in network systems. A new non classification algorithm was developed based on the danger theory model of human immune system (HIS).The abstract model of system algorithm is inspired from HIS cell mechanism mainly, the Dendritic cell behavior and T-cell mechanisms. Classification techniques using k-nearest neighbor (k-NN) or Gaussian Mixture (GMM) almost have the common sense that they believe the neighboring data. The algorithm tested use KDD Cup dataset and the result shows a significant improvement in detection accuracy and reducing the false alerts.

Artificial Immune System (AIS) has been built for a wide range of applications with successful implementation. The bio-inspired systems are best developed and analyzed in the context of a multidisciplinary conceptual framework that provides sophisticated biological models and well-founded analytical principles. In this work, conceptual frameworks for AIS and layered framework for engineering AIS are integrated to introduce a new hybrid conceptual framework to develop AIS systems. The developed framework is used to develop an application for biological inspired intrusion prevention and self healing system and efficient results are achieved.

The security risks of Internet banking have always been a concern to the service providers and users. In this work we analyze user authentication methods being used in various online environments, such as internet banking, electronic transactions and financial services, to identify the characteristics and issues of such authentication methods in order to present a user authentication level system model suitable for different online services. We integrated multi factor authentication with multi layer authentication techniques in order to produce a standard layered multi factor authentication model suitable for different internet banking services based on risk assessment criteria. The produced model consist of 5 level in which each level contain a one or combination of authentication factors such as knowledge based, possession-based or Biometric-based factors. The model then enhanced by adding control information factors, specifically for levels (4, 5), in order to support layering needs. Our paper suggests standard model compared to multi layering guidelines and it shows improvement and fulfillment of authentication needs.

Artificial immune systems have recently been implemented in the field of computer security system particularly in intrusion detection and prevention systems. In this paper researchers present an approach to an intrusion prevention system (IPS) which is inspired by the Danger model of immunology. This novel approach used a multi immune agent system that implements a non-linear classification method to identify the abnormality behavior of network system. The authors look into Dendritic Cell (DC) which is a cell in Innate Immune system (IIS) as a classifier cell. Our approach takes the advantages of multi agent system, Dendritic cell, Cluster-K-Nearest-Neighbor, K-mean and Gaussion mixture methods which are give an autonomous, highly accurate and fast classifier security system. This is based on intelligent agents that exploit known functional features of the immune system and the self-healing system to detect, prevent and heal harmful or dangerous events in network systems A combination of features between the IPS and self healing (SH) mechanism to ensure continuity of the networked systems have been established.

In this paper, software system, design theories and human immune system (HIS) features are used to introduce a novel algorithm for the problem of preventing intrusions and healing the damage which they cause. The HIS features are analyzed and modelled to monitor network systems as to whether the inline activities are behaving abnormally or being attacked. The abnormal activities are prevented and healed by the presented algorithms. We show how the use of biological immune systems, which incorporate an innate, adaptive immune system and self-healing mechanism, can reduce the number of false alerts and heal the damage caused by intrusion. This autonomous system improves the performance of the current Intrusion Prevention System (IPS) and carries on system continuity by using the Self-Healing (SH) mechanism.

This paper describes a new approach for network security based on the combination of biological intrusion prevention and self-healing concepts. The presented system integrates an artificial immune intrusion prevention system for network security inspired by immunological theory known as danger theory. The approach is based upon data inspired by the human immune system (HIS). The IPS analyzes the malicious activities and their effect to trigger the self-healing system. That is detection of the damage caused by malicious activities is used to start the self - healing (SH) mechanism. This system is automated and enhances the fault repair and system recovery.

Biologically - inspired computer security has various techniques to solve the problems that facing computer networks security, such as immune system, diversity, danger theory, virus Epidemiology and non-representational approaches. Immune Systems are fairly complex with some unique schemes and are thus a rich source of concepts, which are applicable to a variety of problems. In this paper a new framework together with a set of paradigms for adaptive immune virtual layers implemented by multi-mobile agents based active monitoring of network systems is proposed. Multi-mobile agents combine features of adaptation, self defending and self monitoring of human immune system, that works in parallel with decentralizes control. Adaptive immune virtual layers system could be implemented by Kernel -assisted mobile agents (processes) that migrate between computers and search for a specific abnormal behavior, and take necessary actions: monitoring each other, detecting attacks, eliminating, circulating, and replicating themselves.