Yousof Al-Hammadi

DCA for bot detection

Ensuring the security of computers is a non-trivial task, with many techniques used by malicious users to compromise these systems. In recent years a new threat has emerged in the form of networks of hijacked zombie machines used to perform complex distributed attacks such as denial of service and to obtain sensitive data such as password information. These zombie machines are said to be infected with a dasiahotpsila - a malicious piece of software which is installed on a host machine and is controlled by a remote attacker, termed the dasiabotmaster of a botnetpsila. In this work, we use the biologically inspired dendritic cell algorithm (DCA) to detect the existence of a single hot on a compromised host machine. The DCA is an immune-inspired algorithm based on an abstract model of the behaviour of the dendritic cells of the human body. The basis of anomaly detection performed by the DCA is facilitated using the correlation of behavioural attributes such as keylogging and packet flooding behaviour. The results of the application of the DCA to the detection of a single hot show that the algorithm is a successful technique for the detection of such malicious software without responding to normally running programs.

Simplified Subspaced Regression Network for Identification of Defect Patterns in Semiconductor Wafer Maps

Wafer defects, which are primarily defective chips on a wafer, are of the key challenges facing the semiconductor manufacturing companies, as they could increase the yield losses to hundreds of millions of dollars. Fortunately, these wafer defects leave unique patterns due to their spatial dependence across wafer maps. It is thus possible to identify and predict them in order to find the point of failure in the manufacturing process accurately. This paper introduces a novel simplified subspaced regression framework for the accurate and efficient identification of defect patterns in semiconductor wafer maps. It can achieve a test error comparable to or better than the state-of-the-art machine-learning (ML)-based methods, while maintaining a low computational cost when dealing with large-scale wafer data. The effectiveness and utility of the proposed approach has been demonstrated by our experiments on real wafer defect datasets, achieving detection accuracy of 99.884% and R2 of 99.905%, which are far better than those of any existing methods reported in the literature.

The evolution of distributed systems towards microservices architecture

Applications developed to fulfil distributed systems needs have been growing rapidly. Major evolutions have happened beginning with basic architecture relying on initiated request by a client to a processing side referred to as the server. Such architectures were not enough to cope up with the fast ever-increasing number of requests and need to utilize network bandwidth. Mobile agents attempted to overcome such drawbacks but did cope up for so long with the growing technology platforms. Service Oriented Architecture (SOA) then evolved to be one of the most successful representations of the client-server architecture with an added business value that provides reusable and loosely coupled services. SOA did not meet customers and business expectations as it was still relying on monolithic systems. Resilience, scalability, fast software delivery and the use of fewer resources are highly desirable features. Microservices architecture came to fulfil those expectations of system development, yet it comes with many challenges. This paper illustrates how distributed systems evolved from the traditional client-server model to the recently proposed microservices architecture. All architectures are reviewed containing brief definitions, some related work and reasoning of why they had to evolve. A feature comparison of all architectures is also provided.

QoS-OLSR protocol based on intelligent water drop for Vehicular ad-hoc networks

In this paper, we address the problem of MultiPoint Relay (MPR) node disconnection due to mobility in Vehicular ad-hoc networks (VANETs) using the cluster-based Quality of Service Optimized Link State Routing (QoS-OLSR) protocol. The protocol uses MPR nodes to establish communication among the clusters. MPR disconnection represents a major challenge in VANETs, due to the frequent change in the network topology. Consequently, the performance of the routing protocol will be weakened as it adversely affects the connectivity level of the network. Thus, our solution is a new cluster-based QoS-OLSR protocol based on intelligent water drop algorithm that is capable of (1) selecting the best set of MPR in terms of QoS (2) dealing with the MPR disconnection as it selects alternatives to assure a connected network (3) maintaining a reliable MPR failure management process. Simulation results demonstrate that the proposed model succeeds in improving the network connectivity and stability, reducing both the overhead and the path length, and increasing the packet delivery ratio compared to the original QoS-OLSR.

Students' interest in STEM education

In this paper we study the interest of students in the United Arab Emirates (UAE) from grade 9 to 12 in Science, Technology, Engineering, and Mathematics (STEM). Surveys were distributed to students who chose STEM tracks and students who chose non-STEM tracks in public and private schools, as well as universities, across the country. The data collected revealed a number of reasons that make students like, or dislike, scientific majors. These reasons include the presence or absence of capable teachers and the choice of the teaching language. The results presented in the paper also focus on differences between public and private institutions, male and female students, as well as nationals and non-nationals. We also compare our findings to similar research done in the USA We show that several factors remain valid in both countries whereas others are specific to each of them.

Spamdoop: A privacy-preserving Big Data platform for collaborative spam detection

Spam has become the platform of choice used by cyber-criminals to spread malicious payloads such as viruses and trojans. In this paper, we consider the problem of early detection of spam campaigns. Collaborative spam detection techniques can deal with large scale e-mail data contributed by multiple sources; however, they have the well-known problem of requiring disclosure of e-mail content. Distance-preserving hashes are one of the common solutions used for preserving the privacy of e-mail content while enabling message classification for spam detection. However, distance-preserving hashes are not scalable, thus making large-scale collaborative solutions difficult to implement. As a solution, we propose Spamdoop, a Big Data privacy-preserving collaborative spam detection platform built on top of a standard Map Reduce facility. Spamdoop uses a highly parallel encoding technique that enables the detection of spam campaigns in competitive times. We evaluate our systems performance using a huge synthetic spam base and show that our technique performs favorably against the creation and delivery overhead of current spam generation tools.

Machine-Learning-Based Identification of Defect Patterns in Semiconductor Wafer Maps: An Overview and Proposal

Wafers are formed from very thin layers of a semiconductor material, hence, they are highly susceptible to various kinds of defects. The defects are most likely to occur during the lengthy and complex fabrication process, which can include hundreds of steps. Wafer defects are generally caused by machine inaccuracy, chemical stains, physical damages, human mistakes, and atmospheric conditions. The defective chips tend to have several unique spatial patterns across the wafer, namely ring, spot, repetitive and cluster patterns. To locate such defect patterns, wafer maps are used to visualize and ultimately lead to better understanding of what happened during the process failure. To identify the unique patterns of defects and to find the point of manufacturing process that causes such defects accurately, nature-inspired model-free machine-learning techniques have been well accepted. This paper thus reviews the theoretical and experimental literature of such models with a focus on model learnability and efficiency-related issues involving data reduction and transformation techniques, which could be seen as the key model properties to deal with big data applications.

Autonomous deployment of mobile sensors network in an unknown indoor environment with obstacles

We developed a Voronoi-based algorithm, called Bio-Inspired Self Organizing Network (BISON), designed to provide a successful deployment of wireless sensor network (WSN) following fast, cost-efficient and self-organizing process, autonomously adapting to the unknown topology of the target environment, and avoiding obstacles discovered in real-time. To limit the power consumed during the deployment, BISON restricts each node to use only locally sensed information to adapt to live-discovered topology while avoiding obstacles and connecting with neighboring nodes. The algorithm is evaluated with respect to several metrics, and simulation results showed faster convergence to a fully connected network with lower deployment costs compared to similar algorithms reported in the literature.

Inverted ant colony optimization for search and rescue in an unknown maze-like indoor environment

We demonstrate the applicability of inverted Ant Colony Optimization (iACO) for target search in a complex unknown indoor environment simulated by a maze. The colony of autonomous ants lay repellent pheromones to speed up exploration of the unknown maze instead of reinforcing presence in already visited areas. The role of a target-collocated beacon signal within the maze is evaluated in terms of its utility to guide the search. Variants of iACO were developed, with beacon initialization (iACO-B), and with increased sensing ranges (iACO-R with a 2-step far-sightedness) to quantify the most effective one. The presented models can be implemented with self-organizing wireless sensor networks carried by autonomous drones or vehicles and can offer life-saving services of localizing victims of natural disasters or during major infrastructure failures.

Secure lightweight ECC-based protocol for multi-agent IoT systems

The rapid increase of connected devices and the major advances in information and communication technologies have led to great emergence in the Internet of Things (IoT). IoT devices require software adaptation as they are in continuous transition. Multi-agent based solutions offer adaptable composition for IoT systems. Mobile agents can also be used to enable interoperability and global intelligence with smart objects in the Internet of Things. The use of agents carrying personal data and the rapid increasing number of connected IoT devices require the use of security protocols to secure the user data. Elliptic Curve Cryptography (ECC) Algorithm has emerged as an attractive and efficient public-key cryptosystem. We recommend the use of ECC in the proposed Broadcast based Secure Mobile Agent Protocol (BROSMAP) which is one of the most secure protocols that provides confidentiality, authentication, authorization, accountability, integrity and non-repudiation. We provide a methodology to improve BROSMAP to fulfill the needs of Multi-agent based IoT Systems in general. The new BROSMAP performs better than its predecessor and provides the same security requirements. We have formally verified ECC-BROSMAP using Scyther and compared it with BROSMAP in terms of execution time and computational cost. The effect of varying the key size on BROSMAP is also presented. A new ECC-based BROSMAP takes half the time of Rivest-Shamir-Adleman (RSA) 2048 BROSMAP and 4 times better than its equivalent RSA 3072 version. The computational cost was found in favor of ECC-BROSMAP which is more efficient by a factor of 561 as compared to the RSA-BROSMAP.