Peering into the Abyss: A Dive into Digital Forensics Research

Published in: Journal

Feb 18, 2026

Heba Saleous Marton Gergely Saed AlRabaee

Exploring ModernBERT for the Classification of Hateful Social Media Texts

Published in: Conference

Dec 12, 2025

Nowadays, social media has been embedded in all aspects of life all over the world. Between standard users taking advantage of convenient communication and content sharing, and organizations leveraging the exposure for marketing and client outreach, the traffic that social platforms have seen in the last decade has spiked. However, as the number of users, and thus the content shared, continues to grow, the amount of potentially harmful material being posted to the public web has also risen. Previous works have explored the potential use of language models to improve the quality of content moderation. This study focuses on ModernBERT, a newer iteration of the BERT model, and compares its performance with handling textual content from various social media platforms to that of DistilBERT, a previously studied model. Across all datasets used within this study, DistilBERT slightly outperformed ModernBERT in terms of precision, recall, F1-score, accuracy, and training/validation time. For Twitter/X, Facebook, and Instagram, DistilBERT achieved accuracies of 90%, 81%, and 75%, respectively , compared to ModernBERT’s 91%, 79%, and 73%. The higher accuracy with the Twitter/X dataset may be attributed to the size of the dataset. These findings highlight the importance of dataset characteristics in model performance and pave the way for future studies across other online platforms and virtual communities, such as online games.

Exploring NLP-based Solutions to Social Media Moderation Challenges

Published in: Journal

Jun 17, 2025

Heba Saleous Marton Gergely Khaled Shuaib

The rise of social media has revolutionized global communication, enabling users and businesses to connect, advertise, and monitor competitors. However, this expansion has also fueled toxic behaviors like hate speech and harassment, exposing innocent users to harmful content while overwhelming human moderators and impacting their well-being. To address these challenges, artificial intelligence (AI) and natural language processing (NLP) have been explored as potential solutions. The aim of this paper is to study existing AI-based moderation approaches to understand which models have been used, their effectiveness, and the challenges they face. This work conducts a targeted systematic literature review of research efforts that present a technical approach to the topic while sharing model results and highlighting the challenges encountered. The findings reveal that AI-driven moderation shows promise by achieving high accuracy but has some issues that need to be addressed, such as dataset imbalance, obstacles and inconsistencies, bias, and misinterpretation of message meanings. By summarizing existing research efforts and identifying key gaps, this study provides insights into the strengths and weaknesses of current AI-based solutions for content moderation.

Surviving the Wild Wild Web: A User’s Playbook to Navigating the Internet's Trickiest Terrains

Published in: Book

Dec 26, 2024

Marton Gergely Ian Grey Heba Saleous

The information security arena is often vague and confusing for internet users, both young and old. New traps are being devised daily, and falling into them can take legal, ethical, financial, physical, and mental tolls on individuals. With increasing cases of fake news, identity theft, piracy, spying, and scams surfacing, this book explains the risks of the internet and how they can be mitigated from a personal and professional perspective. Surviving the Wild Wild Web: A User’s Playbook to Navigating the Internet’s Trickiest Terrains is a readable guide addressing the malicious behaviors within internet cultures. Written in simple and jargon-free language, the book describes ten pillars of information security risks faced by all internet users. Each pillar will be detailed as a story, starting with the roots of the problem and branching out into tangential related issues and topics. Each chapter ends by detailing ways a user can avoid falling victim to cyber threats. It uses a combination of news articles, topical current events, and previously published academic research to underpin the ideas and navigates how users interact with the World Wide Web. The book aims to create a generation of internet-literate readers who can spot the pitfalls of the internet in their personal and professional lives to surf the web safely. This guide will appeal to any individual interested in internet safety, with a potential readership extending to students and professionals in the fields of computer science, information systems, cybersecurity, business, management, human resources, psychology, medicine, education, law, and policy.

Utilization of Artificial Intelligence for Social Media and Gaming Moderation

Published in: Conference

Dec 25, 2023

Heba Saleous Marton Gergely Khaled Shuaib

As the world continues to evolve, technology has proven to be a necessity in the lives of everyone. Evolving beyond professional use, cyberspace is now populated by online communities being used for communication, learning, and entertainment. However, the increased online presence exposes users to a variety of cultures, personalities, and levels of maturity. Some may also seek to cause harm to others through cyberbullying or may display toxic behaviors. This research aims to tackle the growing problem of toxicity and harassment in online environments. The proposed solution will utilize Artificial Intelligence (AI), and more specifically Natural Language Processing (NLP), to moderate communication and detect malicious language and behavior. The efforts shared in this paper specifically present a work-in-progress. For the time being, two models have been tested with a single dataset from Twitter: a Convolutional Neural Network (CNN) and a Recurrent Neural Network (RNN). The results of experimentation show a promising start for the use of NLP in moderation with an 83% accuracy using an RNN.

Uninstall, Noob! Views on Rampant Toxicity in Online Gaming

Published in: Conference

Dec 25, 2023

Heba Saleous Marton Gergely

Video games have become a big part of the digital world, evolving from mere sources of entertainment to entire career paths. Combined with improved device accessibility and implemented network-based features, gamers all around the world can play together any time they want. While the increased social aspects of video games mean that players can make new friends wherever they are in the world, some gamers take advantage of anonymity to harass others for various reasons. As the number of gamers grows over the years, so does the number of toxic behaviors found in online video games. In this research, a survey is conducted on the United Arab Emirates University (UAEU) community to collect their experiences with toxicity and harassment in online video games, as well as player reporting systems. The results show that racism, sexism, and extreme slurs are encountered the most and that current reporting systems are ineffective in the battle to curb toxicity.

Video Games in Digital Forensics

Published in: Book Chapter

Sep 27, 2023

Heba Saleous

As the world continues to move forward, technology has proven to be a necessity in the lives of people all over. Evolving beyond professional use, cyberspace is now being used for communication, learning, and entertainment. One form of entertainment that has spiked in popularity over the years is video games. In addition to providing a leisurely escape from reality, video games have provided a platform for new careers, can be used to spread awareness and raise charity money, and can improve health and education. However, cybercriminals have found that video games also provide more malicious opportunities. For this reason, video games and their consoles need to be considered more in cybersecurity and digital forensics. The objective of this work is to review the literature that has been published so far about video games in the context of digital forensics. The articles included have been categorized in several ways to gain perspective on the current state of research on these topics. The results of the review indicate that much research has been done on how to forensically acquire and analyze video game software and hardware, but not how they can be used maliciously. Additionally, most of the research focused on standard personal computer (PC) games rather than video game consoles.

COVID-19 Pandemic and the Cyberthreat Landscape: Research Challenges and Opportunities

Published in: Journal

Jun 23, 2022

Heba Saleous Muhusina Ismail Saleh AlDaajeh Nisha Madathil Saed AlRabaee Kim-Kwang Raymond Choo Nabeel Al-Qirim

Although cyber technologies benefit our society, there are also some related cybersecurity risks. For example, cybercriminals may exploit vulnerabilities in people, processes, and technologies during trying times, such as the ongoing COVID-19 pandemic, to identify opportunities that target vulnerable individuals, organizations (e.g., medical facilities), and systems. In this paper, we examine the various cyberthreats associated with the COVID-19 pandemic. We also determine the attack vectors and surfaces of cyberthreats. Finally, we will discuss and analyze the insights and suggestions generated by different cyberattacks against individuals, organizations, and systems.

The role of national cybersecurity strategies on the improvement of cybersecurity education

Published in: Journal

May 18, 2022

Saleh AlDaajeh Heba Saleous Saed AlRabaee Ezedin Barka Frank Breitinger Kim-Kwang Raymond Choo

Digital information and telecommunication technologies have not only become essential to individuals’ daily lives but also to a nation’s sustained economic growth, societal well-being, critical infrastructure resilience, and national security. Consequently, the protection of a nation’s cyber sovereignty from malicious acts is a major concern. This signifies the importance of cybersecurity education in facilitating the creation of a resilient cybersecurity ecosystem and in supporting cyber sovereignty. This study reviews a sample from world-leading countries National Cybersecurity Strategic Plans (NCSPs) and analyzes the associated existing cybersecurity education and training improvement initiatives. Furthermore, a proposal to adopt the Goal-Question-Outcomes(GQO)+Strategies paradigm into cybersecurity education and training programs curricula improvement to national cybersecurity strategic goals is presented. The proposal maps cybersecurity strategic goals to cybersecurity skills and competencies using the National Initiative for Cybersecurity Education (NICE) framework. The newly proposed cybersecurity education and training programs’ curricula learning outcomes were generated from the GQO+Strategies paradigm based on the three major cybersecurity strategic goals: Development of secure digital and information technology infrastructure and services, defending from sophisticated cyber threats, and enrichment of individuals’ cybersecurity maturity and awareness. It is highly recommended that cybersecurity university program administrators utilize the proposed GQO+Strategies to align their program’s curriculum to NCSP. Hence, closing the gap that exists with the relevant skills and sustain national cybersecurity workforces.

A Peek at the Digital Forensics Landscape

Published in: Conference

May 11, 2021

Heba Saleous Marton Gergely

As technology becomes more embedded into our lives, criminals have found more opportunities to perform malicious acts. Cybercrimes have become a major concern for the safety and well-being of organizations and communities. To combat these crimes, law enforcement authorities and governments have established cybersecurity and digital forensics teams to investigate incidents. As a result, digital forensics has become a necessity in law enforcement globally. In this preliminary review, we explore existing digital forensics research through reading and reviewing a random sample of fifty publications that appeared when searching for “digital forensics” and similar terms. The different domains, sub-domains, and topics are noted, and observed trends are analyzed. It was found that many of the publications in the sample were published in the last 5 years, focusing on topics related to distributed systems and data analysis. Any remaining issues that need to be addressed are also mentioned to determine the focus for future research.