Imtiaz Parvez

Md. Ifthekhar Hossain, Kazi Abdullah Al Arafat, Bryce Shepard et al.

Malicious URLs pose significant security risks as they facilitate phishing attacks, distribute malware, and empower attackers to deface websites. Blacklist detection methods fail to identify new or obfuscated URLs because they depend on pre-existing patterns. This work presents a hybrid deep learning model named GNN-GAT-LSTM that combines Graph Neural Networks (GNNs) with Graph Attention Networks (GATs) and Long Short-Term Memory (LSTM) networks. The proposed architecture extracts both the structural and sequential patterns of the features from data. The model transforms URLs into graphs through a process where characters become nodes that connect through edges. It applies one-hot encoding to represent node features. The model received training and testing data from a collection of 651,191 URLs, which were classified into benign, phishing, defacement, and malware categories. The preprocessing stage included both feature engineering and data balancing techniques, which addressed the class imbalance issue to enhance model learning. The GNN-GAT-LSTM model achieved outstanding performance through its test accuracy of 0.9806 and its weighted F1-score of 0.9804. It showed excellent precision and recall performance across most classes, particularly for benign and defacement URLs. Overall, the model provides an efficient and scalable system for detecting malicious URLs while demonstrating strong potential for real-world cybersecurity applications.

Alvi Ataur Khalil, Javier Franco, Imtiaz Parvez et al.

Blockchain has become a key technology in a plethora of application domains owing to its decentralized public nature. The cyber-physical systems (CPS) is one of the prominent application domains that leverage blockchain for myriad operations, where the Internet of Things (IoT) is utilized for data collection. Although some of the CPS problems can be solved by simply adopting blockchain for its secure and distributed nature, others require complex considerations for overcoming blockchain-imposed limitations while maintaining the core aspect of CPS. Even though a number of studies focus on either the utilization of blockchains for different CPS applications or the blockchain-enabled security of CPS, there is no comprehensive survey including both perspectives together. To fill this gap, we present a comprehensive overview of contemporary advancement in using blockchain for enhancing different CPS operations as well as improving CPS security. To the best of our knowledge, this is the first paper that presents an in-depth review of research on blockchain-enabled CPS operation and security.

Nur Imtiazul Haque, Md Hasan Shahriar, Md Golam Dastgir et al.

Smart grid (SG) is a complex cyber-physical system that utilizes modern cyber and physical equipment to run at an optimal operating point. Cyberattacks are the principal threats confronting the usage and advancement of the state-of-the-art systems. The advancement of SG has added a wide range of technologies, equipment, and tools to make the system more reliable, efficient, and cost-effective. Despite attaining these goals, the threat space for the adversarial attacks has also been expanded because of the extensive implementation of the cyber networks. Due to the promising computational and reasoning capability, machine learning (ML) is being used to exploit and defend the cyberattacks in SG by the attackers and system operators, respectively. In this paper, we perform a comprehensive summary of cyberattacks generation, detection, and mitigation schemes by reviewing state-of-the-art research in the SG domain. Additionally, we have summarized the current research in a structured way using tabular format. We also present the shortcomings of the existing works and possible future research direction based on our investigation.

Imtiaz Parvez, Maryamossadat Aghili, Arif Sarwat

In the smart grid, smart meters, and numerous control and monitoring applications employ bidirectional wireless communication, where security is a critical issue. In key management based encryption method for the smart grid, the Trusted Third Party (TTP), and links between the smart meter and the third party are assumed to be fully trusted and reliable. However, in wired/wireless medium, a man-in-middle may want to interfere, monitor and control the network, thus exposing its vulnerability. Acknowledging this, in this paper, we propose a novel two level encryption method based on two partially trusted simple servers (constitutes the TTP) which implement this method without increasing packet overhead. One server is responsible for data encryption between the meter and control center/central database, and the other server manages the random sequence of data transmission. Numerical calculation shows that the number of iterations required to decode a message is large which is quite impractical. Furthermore, we introduce One-class support vector machine (machine learning) algorithm for node-to-node authentication utilizing the location information and the data transmission history (node identity, packet size and frequency of transmission). This secures data communication privacy without increasing the complexity of the conventional key management scheme.

Imtiaz Parvez, Arif I. Sarwat, Jonathan Pinto et al.

The uprising interest in multi-agent based networked system, and the numerous number of applications in the distributed control of the smart grid leads us to address the problem of time synchronization in the smart grid. Utility companies look for new packet based time synchronization solutions with Global Positioning System (GPS) level accuracies beyond traditional packet methods such as Network Time Proto- col (NTP). However GPS based solutions have poor reception in indoor environments and dense urban canyons as well as GPS antenna installation might be costly. Some smart grid nodes such as Phasor Measurement Units (PMUs), fault detection, Wide Area Measurement Systems (WAMS) etc., requires synchronous accuracy as low as 1 ms. On the other hand, 1 sec accuracy is acceptable in management information domain. Acknowledging this, in this study, we introduce gossip algorithm based clock synchronization method among network entities from the decision control and communication point of view. Our method synchronizes clock within dense network with a bandwidth limited environment. Our technique has been tested in different kinds of network topologies- complete, star and random geometric network and demonstrated satisfactory performance.