The Malware Detection System using Machine Learning leverages advanced machine learning algorithms to identify and classify malicious software with high accuracy. This system analyzes patterns in program behavior and code features to distinguish between benign and malicious files, enabling early detection of threats. By training on diverse datasets, the model adapts to new and evolving malware strains, making it a proactive tool for cybersecurity. Its efficient and scalable design allows for real-time analysis, providing robust protection against a wide range of cyber threats.
The Real-Time Face Mask Detection System utilizes a Deep Neural Network-based face detector combined with MobileNet V2 to accurately identify individuals wearing or not wearing face masks. Designed for real-time applications, this system quickly processes video streams to detect mask compliance in various settings, ensuring efficient monitoring. The use of MobileNet V2 enables high accuracy with low computational requirements, making it ideal for deployment on devices with limited processing power. This solution addresses safety compliance needs in environments where mask usage is essential.
The Network Anomaly Detection and Intrusion Detection System utilizes deep learning techniques to identify unusual or suspicious network activity, ensuring proactive threat detection. By analyzing vast amounts of network traffic data, the system learns to differentiate between normal behavior and potential intrusions, such as unauthorized access or cyberattacks. Using deep learning models, it adapts to evolving threats, improving detection accuracy over time. Designed for real-time monitoring, this solution enhances network security by swiftly identifying and mitigating intrusions, providing a robust defense against advanced cyber threats.
We developed a robust and scalable Real-Time Vehicle Tracking System using IoT technology. The primary goal was to enable continuous tracking of vehicles and provide real-time data for efficient fleet management. The system includes both hardware and software components, designed to seamlessly capture and transmit vehicle location data to a centralized server, which is then displayed on a user-friendly dashboard. This project emphasized data accuracy, scalability, and ease of use, making it highly adaptable to various types of vehicles and fleet sizes.
Current Research at IIT Delhi: Network Security for Large-Scale Networks using Machine Learning
Supervisor: Prof. Vireshwar Kumar, Department of Computer Science & Engineering