Phisblocker- Adaptive Smishing Detection Model
Year: 2025
Type: dissertation
Abstract: PhishBlocker: Adaptive Smishing Detection Model is a machine learning-based system designed to detect and prevent SMS phishing (smishing) attacks. Smishing is a growing cybersecurity threat where attackers use deceptive text messages to trick users into revealing personal information or clicking malicious links. This project implements an adaptive detection pipeline that includes: Data preprocessing and text cleaning Feature extraction using natural language processing (NLP) Evaluation of multiple machine learning models including Logistic Regression, Random Forest, SVM, and Neural Networks The final model continuously adapts to new smishing patterns by learning from updated datasets, ensuring high detection accuracy and minimal false positives. PhishBlocker can be integrated into mobile security apps, telecom filtering systems, or enterprise security tools to protect users from SMS-based phishing attacks in real time. Key Features: Adaptive learning for evolving phishing patterns NLP-based text preprocessing and feature engineering Multi-model evaluation for optimal performance Practical deployment for real-world mobile security Repository: GitHub – PhishBlocker References:[1] Hosseinpour, M., & Das, A. (2025). Multi-signal smishing detection using contextual embeddings. IEEE Transactions on Information Forensics and Security.
Authors: CHOUDHARY, ATUL, Vadhera, Ms. Renu
Language: English
Topic: Spam and Phishing Detection
Subfield: Information Systems
Field: Computer Science
Domain: Physical Sciences
Open Access status: green
OpenAlex ID: W7111001653
Cites:
Cited by:
Related to: