Prof. Khaled Shaban, as a Primary Research Mentor, and Dr. Alaa Abdellatif, as a Postdoctoral Fellow, are awarded two years funding for their proposal in the seventh cycle of Postdoctoral Research Award (PDRA) from Qatar National Research Fund (QNRF). The project is titled “AI-driven Secured Demand Response in Next Generation Smart Grid Using Blockchain and 5G Networks”. It is one of two PDRA proposals awarded by QNRF to Qatar University in this cycle. More details on the project can be found here.
Dr. Khaled Khan and Dr. Noora Fetais from the Department of Computer Science and Engineering (CSE) have been awarded a patenttitled “Methods and Systems for Monitoring Network Security” in collaboration with KINDI Center for Computing Research in the College of Engineering at Qatar University.
The Qatar National Research Funds has supported this research under National Priority Research Program (NPRP8-531-1-111). Dr. Khaled and Dr Noora acted as the Lead PI and PI of the project respectively. Dr. Armstrong Nhlabatsi from KINDI also participated in the research project. They collaborated with the researchers from the University of Canterbury (New Zealand) and the University of Queensland (Australia).
Modern networks are becoming more and more dynamic, such as frequent changes compared to the traditional static networks (e.g., hosts addition and removal, vulnerability change, applications and services update, and attack surface change). In a dynamic network, the configuration of at least one of the hosts or edges changes over time. The dynamic network is a network selected from a group of configured components including cloud computing, a software-defined networking arrangement, or an Internet of Things network. As network components change over time, the security posture of the network also changes, as vulnerabilities associated with the network components shift accordingly. Hence, it is of paramount importance to be able to assess the security of dynamic networks in order to understand and further enhance the security.
This patented approach is a new technique for monitoring the security of a computing network, which includes a plurality of hosts and a plurality of edges which link connected hosts. The method comprises capturing and storing network state information in response to at least one of the time-driven trigger, an event-driven trigger or a user-driven trigger. The method further comprises storing security-related data which is indicative of the change in the security of the network during the time window for a user to monitor the change in the security of the network. Detecting a change in the security of the network comprises at least one of the following events: the addition of a new host to the network; the removal of a host from the network; the addition of a new edge to the network; the removal of an edge from the network; the addition of a vulnerability to a host in the network; or the removal of a vulnerability from a host in the network. The method calculates at least one security metric for the network and a weight value for at least one of the components in the network. The approach is capable of capturing such critical changes and reflecting the modified security posture in order to precisely assess the security of dynamic networks.
Tahani Abu Musa, a PhD student at our department, supervised by Prof. Abdelaziz Bouras, has received the “IFIP WG5.1 Award of the Best Doctoral Proposal” during the IFIP 18th International Conference on Product Lifecycle Management (PLM) held on 11-14 July 2021, Curitiba, Brazil.
Tahani’s presented research plan titled “Anomaly Detection in Blockchain-enabled Supply Chain: A Deep Learning Approach” deals with the development of an anomaly detection framework, for detecting anomalous transactions in business processes. Her research work focuses on three objectives:
Improve the accuracy of anomaly detection in the Supply Chain large volume of transactions, using a deep learning-based approach.
Provide anomalies classification, to improve the Supply Chain business processes, by utilizing Ontology as a smart knowledge base.
Enhance and secure the Supply Chain information system by incorporating Blockchains in the global network and building more reliable Smart Contracts.
A research team from CSE department has won the first place at Track 2 (Proof of concept and Demos) of the 2nd annual Artificial Intelligence National Competition announced today by the organizing committee. The team consists of Nandhini Subramanian (Research Assistant and former CSE MSc student), Dr. Omar Elharrouss, Post Doc Researcher at our department, and Prof. Somaya Al Maadeed. The winning demo is titled “Reversible Image Steganography Using Auto Encoder-Decoder Deep Learning Methods”, which is part of QNRF NPRP11S-0113- 180276 project.
Image steganography is used to hide secret images inside the cover image in plain sight. Traditionally, the secret data is converted into binary bits and the cover image is manipulated statistically to embed the secret binary bits. Overloading the cover image may lead to distortions and the secret information may become visible. Hence the hiding capacity of the traditional methods are limited. In their project, an unique, light-weight and simple deep convolutional auto encoder architecture is proposed to embed the secret image inside the cover image as well as to extract the embedded secret image from the reconstructed stego image.
The AI national competition is a national competition challenging students, developers, professionals, and researchers to develop and demonstrate how humans can collaborate with powerful Artificial Intelligence (AI) technologies to tackle some challenges for different applications. It raises awareness of AI technologies in Qatar, supports building local capacity in this timely and crucial area, and provides a platform for participants to share AI ideas and applications.
Prof. Abdelaziz Bouras and Dr. Abdulaziz Al-Ali co-edited a new Springer book on “Data Analytics for Cultural Heritage – Current Trends and Concepts”. The book highlights challenges and solutions related to the improvement of the data acquisition, data enrichment, and data management processes in the cultural heritage data lifecycle pipeline. It mainly focuses on the use of advanced artificial intelligence and machine learning technologies with an emphasis on recent applications related to deep learning for visual recognition, generative models, natural language processing and super-resolution.