Papers by Mohammad Awawdeh
Harnessing MQTT-SN in IoT, 2024
The advent of new technologies such as the Internet of Things (IoT) continues to create what can ... more The advent of new technologies such as the Internet of Things (IoT) continues to create what can be referred to as a ‘global village’ or a ‘borderless’ world that improves performance, eases processes, and increases creativity in all areas of work. At the same time, however, the increase in the number of connected devices poses some challenges as well. For instance, issues of effective data transfer and security stand out. This paper discusses the utilization of the MQTT-SN (Message Queuing Telemetry Transport for Sensor Networks) IoT protocol focusing more on the fact that it was built for small low-power devices without many resources that are the norm in many IoT environments. The discusses the protocols publish/subscribe model and explores the possibility of using UDP to discuss the merits of sensor network communication.
Furthermore, the paper analyzes the existing weaknesses of the advanced IoT system and more importantly, stresses on the need of having Intrusion Detection Systems (IDS) and Intrusion Prevention Systems (IPS) to mitigate potential attacks. This study embraces a literature survey, methodology, and real-world implementation examples to provide the complete picture concerning MQTT-SN in IoT and the respective measures that can be put in place to mitigate risks to these interlinked networks. The results presented draw conclusions confirming that such systems may require additional efforts into the development of both communication protocols and their protective features as the application of such systems is intended to be prolong.
AI-based identity verification through behavioral biometrics, Dec 14, 2024
With the increased adaptability of remote work patterns, secure and efficient identity verificati... more With the increased adaptability of remote work patterns, secure and efficient identity verification has also become a paramount concern. The traditional model of authentication involving the use of passwords or security tokens fails to provide any continuous verification of the user and is also prone to hacking attempts. Behavioral biometrics, especially keystroke dynamics and mouse movement patterns, offer an effective alternative as they allow for unobtrusive user authentication that is based on the individual user's behavior and is therefore continuous. This paper explores the application of Long Short-Term Memory (LSTM) networks, a sequence-based AI model, for studying and differentiating behavioral biometrics. We are using freely available data sets of keystroke and mouse dynamics to design and test an LSTM based system which is capable of making a distinction between users and imposters.
We have shown that LSTM networks are significantly better in handling time series data such as state transition sequences than other statistical machinery traditional machine learning methods, such as Random Forests and Support Vector Machines, where they scored 89% accuracy between normal user operations and abuse activity. This aspect of the research addresses the reason why LSTM networks are appropriate for live remote identity verification systems, which is their ability to learn long strips of sequences and the behavioral flow. The aim of the study is to expand the systems secure authentication solutions based on artificial intelligence systems that can be integrated to facilitate remote working in any sector for enhanced security.
Uploads
Papers by Mohammad Awawdeh
Furthermore, the paper analyzes the existing weaknesses of the advanced IoT system and more importantly, stresses on the need of having Intrusion Detection Systems (IDS) and Intrusion Prevention Systems (IPS) to mitigate potential attacks. This study embraces a literature survey, methodology, and real-world implementation examples to provide the complete picture concerning MQTT-SN in IoT and the respective measures that can be put in place to mitigate risks to these interlinked networks. The results presented draw conclusions confirming that such systems may require additional efforts into the development of both communication protocols and their protective features as the application of such systems is intended to be prolong.
We have shown that LSTM networks are significantly better in handling time series data such as state transition sequences than other statistical machinery traditional machine learning methods, such as Random Forests and Support Vector Machines, where they scored 89% accuracy between normal user operations and abuse activity. This aspect of the research addresses the reason why LSTM networks are appropriate for live remote identity verification systems, which is their ability to learn long strips of sequences and the behavioral flow. The aim of the study is to expand the systems secure authentication solutions based on artificial intelligence systems that can be integrated to facilitate remote working in any sector for enhanced security.