Malware Detection in Encrypted Traffic Through Machine Learning
In an ever-evolving landscape of cyber threats, this project introduces a proactive approach to enhance network security by detecting malware within encrypted traffic. The problem at hand is the stealthy infiltration of malicious activities that evade conventional detection methods. This project uses machine learning and deep learning techniques to identify and mitigate threats such as ransomware, cryptojacking, remote access Trojans, phishing attempts, data exfiltration, botnets, generic malicious behavior, malicious domains, and suspicious network traffic patterns. This research offers a systematic framework for feature engineering and model development by meticulously analyzing system logs and network metadata. Utilizing Python, Jupiter Notebook, and relevant libraries, the project presents a comprehensive solution for transforming raw data into actionable insights, aiding early detection and prompt response to potential threats. The expected results encompass successfully training and evaluating machine learning models to differentiate between normal and malicious network activities, reinforcing network security and protecting critical information assets in a constantly evolving cybersecurity landscape.
Keywords: Malwares ,Machine Learning
Tools: Python, Juypternotebook, Pandas, Scikit-learn, TensorFlow, PyTorch, Tensor FlowServing, ONNX Runtime
Department: Department of Computer Science
Project Team Members
| Name |
Email |
|
Muhammad Irfan Khan
|
irfan2020@namal.edu.pk |
Project Poster
