Malware Detection Using Machine Learning & Deep Learning

Detects malicious URLs using Logistic Regression and malware using deep learning model

Project Description 

Developed a comprehensive Malware Detection System that identifies malicious URLs and malware-infected files using both traditional machine learning and deep learning techniques. The system uses Logistic Regression for detecting malicious URLs based on extracted textual features, and a TensorFlow-based deep learning model for classifying malware files. The project demonstrates the integration of classical ML algorithms and neural networks to build a robust cybersecurity solution.

Features 

• Uses Logistic Regression to classify URLs as safe or malicious.

• Deep learning model built using TensorFlow to detect malware in files.

• Text vectorization (e.g., TF-IDF), scaling, and data transformation.

• Combines traditional ML with deep learning for improved detection capability.

• Lightweight Logistic Regression model for fast URL detection.

• Accuracy, precision, recall, and confusion matrix analysis.

Tech Stack

• Python

• Scikit-learn (Logistic Regression)

• TensorFlow / Keras

• Pandas, NumPy

• TF-IDF Vectorization

• Matplotlib / Seaborn (for visualization)

System Requirements

• Python 3.10+

• Anaconda

• Libraries: numpy, pandas, scikit-learn, matplotlib

• No GPU required

Deliverables 

• Jupyter Notebook

• Dataset

• Setup over video call

• WhatsApp support