Graduate Students Supervised

1. Jawaher Abdullah Saeed Alqahtani
   Degree: Maser
   Title: Steganalysis Algorithm for PNG Images Based on the Fuzzy Logic Technique
   Citation: Jawaher alqahtani, Daniyal Alghazzawi and Li Cheng. (2016). "Steganalysis Algorithm for PNG Images Based on Fuzzy Logic Technique", International Journal of Network Security & Its Applications (IJNSA), Vol. 8, No. 6, November 2016, Page: 1-15, ISSN: 0975 - 2307. DOI: 10.5121/ijnsa.2016.8501. [Link]
   
   [+] Abstract

   Professional criminals need the ability to exchange messages confidentially, and as a result, have exploited the rapid advances in information and communication technology. A prevalent method of doing so is Steganography – the process of hiding a secret message into media. The message can be embedded into any medium (text, image, audio or video). To detect hidden information, tools are used for discovery and analysis. As a counter-measure, tools have been developed in order to detect hidden information form digital media such as text, image, audio or video files. Images (PNG, JPEG, GIF, and BMP) are famously used for steganography. Research in the field has revealed that there are few pre-existing studies done on PNG images and this research will contribute to the body of knowledge by undertaking an increased focus on the PNG format. An experiment was conducted which showed that there are narrow gaps hindering the ability of stenographic tools to detect hidden elements. As such, this research aims to design an algorithm based on artificial intelligence (AI) that is able to detect hidden information embedded by any steganography tool in PNG images. However, the efficiency and performance of previous approaches found in the field's literature have shown room for improvement. In this research, we focus on algorithm design for optimum efficiency of hidden message detection in PNG files. In more detail, the techniques examined are a novel hybrid model developed based on ANFIS and MLP techniques, Support Vector Machines (SVMs), Neural Networks (Multi-Layer Perceptrons MLPs) and Adaptive Neuro-Fuzzy Inference Systems of the Sugeno Type (ANFIS). These techniques are compared on the basis of the resulting confusion matrices, as well as by using the Receiver Operating Characteristic (ROC) curves. Finally, we introduce our message detection system for PNG files based on the LSB approach and present its usability in different case scenarios.

   
   
2. Budoor Salem Edhah
   Degree: Maser
   Title: Secret Communication on Facebook Using Image Steganography
   Citation: Budoor Edhah, Daniyal Alghazzawi, Li Cheng. (2016). "Secret Communication on Facebook Using Image Steganography: Experimental Study", International Journal of Computer Science and Information Security, Vol: 14, No: 10, October 2016, ISSN 1947–5500. [Link] 
   
   [+] Abstract

   Facebook is a popular online social network that provides means for connecting people all over the world to communicate together on one set through chatting, sharing photos, documents, and videos. The widespread of Facebook globally makes it such an attractive medium for image steganography, especially with millions of images uploaded daily which further obscure steganography in the uploaded images. Transmitting photos through Facebook enforces image processing to be applied to the uploaded photos prior their publication which is in consequences alters the original features of the uploaded images; thus, leads to the secret message loss if any. Few researches have been conducted to perform steganography on Facebook such as SecretBook algorithm. However, this algorithm restricts the payload capacity up to 140 characters and the type of uploaded photo. This thesis aims to propose an image steganography method that involves an additional JPEG compression step based on an extracted Facebook quantization table done prior hiding with JPHide and JPSeek algorithm. The proposed method allows JPEG steganography over Facebook with higher size of secret information hiding while maintaining the image quality; at least to the human visual system.

   
   
3. Sahar Ahmed Fadhl Aldhaheri
   Degree: Maser
   Title: DeepDCA: Intrusion Detection over IoT Based on Artificial Immune System and Deep Learning
   Citation : Sahar Aldhaheri, Daniyal Alghazzawi, Li Cheng, Ahmed Barnawi, Bandar Alzahrani, Abdullah Al-Barakati. (2020). "DeepDCA: Novel Network-Based Detection of IoT Attacks Using Artificial Immune System". Applied Sciences, Vol. 10, No. 6, March 2020. DOI: 10.3390/app10061909. (ISI Impact Factor:2.217) [Link]
   
   [+] Abstract

   Recently Internet of Things (IoT) attains tremendous popularity, although this promising technology leads to a variety of security obstacles. The conventional solutions do not suit the new dilemmas brought by the IoT ecosystem. Conversely, Artificial Immune Systems (AIS) is intelligent and adaptive systems mimic the human immune system which holds desirable properties for such a dynamic environment and provides an opportunity to improve IoT security. In this work, we develop a novel hybrid Deep Learning and Dendritic Cell Algorithm (DeepDCA) in the context of an Intrusion Detection System (IDS). The framework adopts Dendritic Cell Algorithm (DCA) and Self Normalizing Neural Network (SNN). The aim of this research is to classify IoT intrusion and minimize the false alarm generation. Also, automate and smooth the signal extraction phase which improves the classification performance. The proposed IDS selects the convenient set of features from the IoT-Bot dataset, performs signal categorization using the SNN then use the DCA for classification. The experimentation results show that DeepDCA performed well in detecting the IoT attacks with a high detection rate demonstrating over 98.73% accuracy and low false-positive rate. Also, we compared these results with State-of-the-art techniques, which showed that our model is capable of performing better classification tasks than SVM, NB, KNN, and MLP. We plan to carry out further experiments to verify the framework using a more challenging dataset and make further comparisons with other signal extraction approaches. Also, involve in real-time (online) attack detection.

    

   Citation : Sahar Aldhaheri, Daniyal Alghazzawi, Li Cheng, Ahmed Barnawi, Bandar Alzahrani. (2020). "Artificial Immune Systems approaches to secure the internet of things: A systematic review of the literature and recommendations for future research". Journal of Network and Computer Applications. DOI: 10.1016/j.jnca.2020.102537 (ISI Impact Factor: 5.273) [Link]
   
   [+] Abstract

   As the Internet of Things (IoT) recently attains tremendous popularity, this promising technology leads to a variety of security challenges. The traditional solutions do not fit the new challenges brought by the IoT ecosystem. Although the development's area of Artificial Immune Systems (AIS) provides an opportunity to improve security issues and create a fertile and exciting environment for further research and experiments, there is not any systematic and comprehensive study about analyzing its importance for IoT environment. Therefore, this work aims to identify, evaluate, and perform a comprehensive study of empirical research on the studies of AIS approaches to secure the IoT environment. The relevant and high-quality studies are addressing using three research questions about the main research motivations, existing solutions, and future gaps and directions. The AIS approaches have been divided into three main categories based on IoT layers, and detailed classifications have also been included based on different parameters. To achieve this aim, the authors use a systematic literature review (SLR) as a powerful method to collect and critically analyze the research papers. Also, the authors discuss the selected studies and their main techniques, as well as their benefits and drawbacks in general. This research process strives to build a knowledge base for AIS solutions under the umbrella of IoT security and suggest directions for future research.