- Analyzes supervised, unsupervised, and hybrid ML approaches for phishing detection
- Reviews feature engineering strategies used in URL and content-based models
- Compares model performance trends across classical ML and DL methods
- Identifies open research challenges in phishing detection systems
- Covers ML use cases in networking: traffic prediction, intrusion detection, and optimization
- Summarizes common algorithms and DL architectures used in intelligent networks
- Discusses key limitations: data quality, scalability, explainability, and deployment
- Outlines future research directions for secure and adaptive networking systems
- Published as part of the 2023 Undergraduate Research Day proceedings
- Represents scholarly contributions and academic engagement at UTPB
- Highlights research communication through formal university proceedings
- Documents academic output and participation in undergraduate research forums