Robust Phishing URL Detection using Hybrid Deep Learning Models
A Wristwatch-Based Real-Time Monitoring, Tracking, and Emergency Response System for Fishermen by Integrating Sensor Technologies and Dual Signal Communications
E-Tendering System using Blockchain
An Overview of Hacking as a Service (HaaS) in Africa
Transforming VLSI Design with AI: Pioneering the Future of Chip Technology
Robust Phishing URL Detection using Hybrid Deep Learning Models
Transforming VLSI Design with AI: Pioneering the Future of Chip Technology
E-Tendering System using Blockchain
A Wristwatch-Based Real-Time Monitoring, Tracking, and Emergency Response System for Fishermen by Integrating Sensor Technologies and Dual Signal Communications
An Overview of Hacking as a Service (HaaS) in Africa
An Overview of Hacking as a Service (HaaS) in Africa
Transforming VLSI Design with AI: Pioneering the Future of Chip Technology
A Wristwatch-Based Real-Time Monitoring, Tracking, and Emergency Response System for Fishermen by Integrating Sensor Technologies and Dual Signal Communications
Robust Phishing URL Detection using Hybrid Deep Learning Models
E-Tendering System using Blockchain
Phishing is one of the most common cybersecurity attacks that infects individuals and organizations globally. Malicious URLs are used by attackers to deceive users and extract private information, such as login credentials, financial details and other sensitive data. The conventional detection methods, such as blacklisting and heuristic-based approaches, are becoming progressively ineffective. This paper introduces a new hybrid deep learning architecture that incorporates Convolutional Neural Networks (CNN), Recurrent Neural Networks (RNN), and Artificial Neural Networks (ANN) to detect phishing URLs with high accuracy. In contrast to current literature that targets single models or restricted mixtures, the present approach ventures a complete architecture integrating the benefits of spatial, sequential, and classification learning. The model is trained on a balanced dataset of more than 11,000 URLs, using 32 features that represent lexical, domain, content, and behavioral characteristics. The hybrid model (CNN+RNN+ANN) resulted in an accuracy rate of 96.41%, surpassing standalone and other hybrid models. Enhancements in the future may include incorporating transformer models, such as BERT or GPT, for better contextual awareness and real-time threat identification.
Fishermen face significant risks at sea without effective safety measures, including harsh conditions, unpredictable weather, and health emergencies. This system uses RFID technology integrated into a wristwatch to offer real-time monitoring and support, enhancing fishermen's safety and well-being. By addressing these challenges, the system aims to reduce the risks associated with their perilous occupation. This safety system employs GSM communication along with various environmental and health monitoring sensors to keep track of the fisherman's environment and health conditions. The RFID wristwatch is equipped with sensors that continuously monitor conditions such as temperature, humidity, water quality, heart rate, body temperature, and consciousness based on body movement. Data is transmitted through GSM to a central monitoring station, allowing for timely interventions and alerts when anomalies are detected. An intelligent switching mechanism optimizes communication by automatically switching from RF signals to acoustic signals depending on whether the fisherman is on the surface or underwater. Acoustic signals travel longer distances without disturbance underwater but are easily affected by objects in the air, while RF signals travel easily in the air but fade underwater due to water constituents. This switching ensures robust connectivity, with signals reaching the central station through a buoyant relay unit regardless of the fisherman's location. The system facilitates real-time monitoring of environmental conditions and vital signs, enabling timely interventions and alerts. The intelligent switching mechanism ensures that communication is effectively maintained, allowing signals to reach the central monitoring station in various environments, thereby safeguarding the fisherman's safety. By continuously monitoring their health and surroundings, advanced technological solutions ensure the well-being of fishermen both at sea and underwater.
Blockchain technology is set to revolutionize e-tendering by enhancing security, transparency, and cost-effectiveness. Traditional tendering methods, often reliant on paper-based processes or centralized digital systems, are prone to fraud, fake documentation, lack of transparency, and bureaucratic delays. Blockchain-based e-tendering addresses these challenges by eliminating intermediaries, reducing corruption, and fostering trust in the bidding process. By leveraging Distributed Ledger Technology (DLT) and smart contracts, block chain ensures that all transactions are immutably recorded, tamper-proof, and verifiable. This technology mitigates risks associated with data manipulation, unauthorized alterations, and biased decision-making. Automated procurement through smart contracts streamlines workflows, minimizes manual intervention, reduces operational costs, and expedites decision-making. This research explores the fundamentals, benefits, and challenges of blockchain applications in e- tendering, analysing various consensus mechanisms, cryptographic security models, and interoperability issues. By utilizing blockchain- powered e-tendering solutions, organizations can cut costs, minimize fraudulent risks, and ensure a transparent and fair bidding process. The study serves as a foundation for future research on innovative procurement models driven by blockchain and provides insights for government agencies, enterprises, and technology innovators seeking to modernize their procurement systems.
Hacking as a Service (HaaS) in Africa presents a growing concern, marked by the increasing availability of cybercrime tools and services. This emerging model exploits diverse socio-economic factors, leading to enhanced access for individuals and groups to perpetrate cyberattacks without substantial technical expertise. The prevalence of cybercrime powered by HaaS threatens the economic stability, security, and privacy of individuals and businesses across the continent. Despite advancements in internet penetration and digital adoption, many African nations remain inadequately prepared to combat these rising threats, exacerbating the vulnerability of their digital environments. The significance of this work lies in addressing the multi-dimensional implications of HaaS on African societies. By undertaking a comprehensive overview, this paper aims to illuminate the various facets of HaaS, including its operational mechanics, associated risks, and the socio-economic contexts that facilitate its proliferation. Furthermore, it seeks to identify strategic recommendations for mitigating these threats and fortifying cybersecurity measures. Ultimately, understanding the nuances of HaaS will aid policymakers, businesses, and civil society in fostering a more secure digital landscape conducive to economic growth and social development.
The use of Artificial Intelligence (AI) in VLSI design has greatly improved the design process. AI techniques like machine learning, deep learning, and neural networks can be applied to various tasks such as optimization, placement, routing, and verification. The implementation of these techniques can enhance the efficiency and accuracy of products while reducing the amount of manual labor required and the design time. AI tools can also identify faults and suggest solutions effectively. The major benefit of AI is its ability to analyze vast amounts of data. Machine Learning algorithms are used for this purpose. Different AI techniques are used for processes like logic design, logic synthesis, physical design and fabrication. This paper examines the challenges of the VLSI design process and the impact of AI on it. This paper explores the AI/ML techniques and tools used in VLSI design, as well as the evolution of AI in this field. Additionally, it discusses the challenges faced in integrating AI into VLSI design.
