• Samruddhi Babasaheb Shinde
• Dr. Ms. S. P. Pawar

In an era where online security is paramount, this project aims to develop a robust system for detecting the security status of web links in real-time. The proposed solution leverages a browser extension equipped with four distinct machine learning algorithms - Support Vector Machines (SVM), Random Forest, Boosting, and Multilayer Perceptron (MLP). Each algorithm contributes its unique strengths in analyzing various features associated with web links, providing a comprehensive evaluation of their security. The project begins by collecting a diverse dataset containing labeled instances of secure and insecure links, incorporating a wide range of features such as URL structure, SSL/TLS certificate information, and historical threat intelligence data. The dataset is then used to train and fine-tune each algorithm, optimizing their ability to accurately classify links into secure and insecure categories. Following the individual training of the algorithms, a novel approach is introduced to enhance overall accuracy - ensemble learning. The ensemble model employs a Voting algorithm that combines the predictions of SVM, Random Forest, Boosting, and MLP. This collaborative decision-making process maximizes the strengths of each algorithm, mitigating potential weaknesses and creating a more resilient and reliable link security detection system. The browser extension seamlessly integrates into users' web browsers, providing real-time feedback on the security status of links encountered during browsing. Users are alerted to potential security threats, allowing them to make informed decisions when interacting with web content. The project's success is evaluated through extensive testing and validation using diverse datasets and real- world scenarios. The overall accuracy of the system is measured, demonstrating the effectiveness of the ensemble learning approach in enhancing link security detection. The results of this project contribute to the ongoing efforts to enhance online security and empower users with the tools needed to navigate the digital landscape securely.

: Link Security, Ensemble Learning, Machine Learning, Support Vector Machines (SVM), Random Forest, Boosting, Multilayer Perceptron (MLP), Voting Algorithm, Browser Extension

"Subterfuge Sentry: Guarding Against Sneaky Malware Tactics", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.11, Issue 4, page no.p201-p205, April-2024, Available :http://www.jetir.org/papers/JETIR2404G26.pdf

"Subterfuge Sentry: Guarding Against Sneaky Malware Tactics", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.11, Issue 4, page no. ppp201-p205, April-2024, Available at : http://www.jetir.org/papers/JETIR2404G26.pdf