Saimul Hoque Sawon
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Saimul Hoque Sawon has a total of 5 co-authors. Here are the top co-authors by number of shared publications:
- Badiuzzaman Biplob
International Islamic University Chittagong, Bangladesh
1 shared publication - Intiser Farhat Bin Islam
International Islamic University Chittagong, Bangladesh
1 shared publication - Jahedul Islam
International Islamic University Chittagong, Bangladesh
1 shared publication - Mahin Ahmed Rahi
International Islamic University Chittagong, Bangladesh
1 shared publication - Mohammad Jashim Uddin
International Islamic University Chittagong, Bangladesh
1 shared publication
Latest Publications
- Open Access
- 14 July 2025
- Published by MDPI AG in Preprints.org
An Introduction to Rule-Based AI Agents for Detecting Phishing Emails
Phishing emails are one of the most common cyber threats that often exploit human error, and lead to unauthorized control, such as misuse of private sensitive data. Conventional spam filters commonly miss more elaborate phishing attacks because they are based around outdated techniques such as blacklists and keyword matching. In this paper, we provide a brief introduction on the application of rule-based artificial intelligence (AI) agents to detecting phishing emails. Based on a thorough examination of the literature and a demonstration example, this paper considers rule-based systems in functioning, effectiveness and any current role in email security systems. The results show that while rule-based AI lacks the adaptability of machine learning models, they offer transparency, interpretability, and ease of deployment, making them suitable for entry-level or hybrid phishing detection systems.
- 14 July 2025
- Published by MDPI AG in Preprints.org
Open AccessAn Introduction to Rule-Based AI Agents for Detecting Phishing Emails
Phishing emails are one of the most common cyber threats that often exploit human error, and lead to unauthorized control, such as misuse of private sensitive data. Conventional spam filters commonly miss more elaborate phishing attacks because they are based around outdated techniques such as blacklists and keyword matching. In this paper, we provide a brief introduction on the application of rule-based artificial intelligence (AI) agents to detecting phishing emails. Based on a thorough examination of the literature and a demonstration example, this paper considers rule-based systems in functioning, effectiveness and any current role in email security systems. The results show that while rule-based AI lacks the adaptability of machine learning models, they offer transparency, interpretability, and ease of deployment, making them suitable for entry-level or hybrid phishing detection systems.