ASAlycia Sebastian

Alycia Sebastian

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Alycia Sebastian has a total of 7 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    EXPLAINABLE ARTIFICIAL INTELLIGENCE MODELS FOR INTRUSION DETECTION SYSTEMS TO IMPROVE THE EFFICIENCY AND INTERPRETABILITY OF BLACK BOX MODELS

    by Alycia Sebastian

    In the field of cybersecurity, Intrusion Detection Systems (IDS) are commonly used to prevent and minimize threats. Systems for detecting intrusions aid in preventing threats and vulnerable points from entering computer networks. Many Machine Learning (ML) techniques are available for assisting development of IDS that perform effectively. In a broad range of tasks, ML based systems have demonstrated improved learning performance. But, the problem with the certain cutting-edge models is that they lack in explanation ability, transparency, and reliability. Explainable AI (XAI) approaches are employed in order to comprehend and clarify these AI models to security analysts. The present study proposes an architecture that uses SHAP for Intrusion detection Systems (IDS) to increase the interpretability of the model by extracting the explanations from the black box models like XGBoost, AdaBoost, Support Vector Machines (SVM) and Random Forest (RF) algorithms. The explanations provided by the SHAP analysis are validated with filter based Feature selection method. The experiment’s findings show that the XGBoost model outperforms the other ML models and the SHAP analysis is performed for the ML model to study the efficacy of the explanations and the importance of features.


  • Open Access

    Unveiling the Factors Influencing Social Media Usage Among A'Sharqiyah University Students: Exploring Impacts and Pathways to Optimization

    by Hamed Al Hajri, Salim Al Hajri, Alycia Sebastian

    Social media networks facilitate global connectivity and communication by providing platforms for users to interact, share information, and build communities online. This study aims to explore the impact of utilizing Social Media Networks (SMNs) on the academic attainment of A’Sharqiyah University students in the Sultanate of Oman. It recognizes the global significance of SMNs in modern society, emphasizing their role in communication, content sharing, and fostering connections. To achieve this, a structured questionnaire was formulated to collect primary data from 300 participants utilizing a purposive sampling technique, and its reliability was assessed through Cronbach's Alpha. The study formulated and tested four hypotheses via linear regression and one-sample t-tests. Results indicated overall satisfaction among participants and their intention to continue using SMNs for educational purposes. However, factors like perceived ease of use, usefulness, and reliability surfaced as key influencing factors in their decisions. This study offers valuable insights for practitioners and policymakers, pinpointing crucial dimensions that need emphasis to improve the utilization of SMN with the goal of enhancing students' academic achievements.

  • Designing an E-Voting System Architecture Using the STAP Protocol

    by Edwin Shalom Soji, S. Karthik, S. Silvia Priscila, D. Kerana Hanirex, S. Suman Rajest, Alycia Sebastian

    E-voting is an innovative strategy that empowers citizens to vote for preferred candidates through secure electronic platforms. Implemented across various countries, e-voting systems are tailored to meet specific national requirements. This paper introduces a distinctive approach to the e-voting process, incorporating rigorous verification from government servers and a reliable authentication mechanism to ensure the integrity and security of both e-voting machines and voters’ choices. The system employs a Specialized Security Key Algorithm to provide robust security for voters and the e-voting infrastructure. Python and SPSS were used to analyze data and validate security measures, while MS Excel was used to organize and visualize the data. The likelihood of communication channel breaches between the system’s central server and the e-voting machines is minimized, eliminating significant data breach risks. By adhering to a carefully crafted architectural approach, this system enhances efficiency and achieves superior accuracy and throughput levels, outperforming other e-voting systems. The core methodologies employed in the system comply with stringent security standards and protocols, with all analyses and simulations verified through tools like Python, SPSS, and Excel. This architectural approach significantly elevates the security framework of the e-voting system, making the entire process more secure, reliable, and tailored to modern democratic needs.