Got an opportunity for 6-Weeks Remote Internship Program under Dr. Balaji Rao. Played a vital role in the development of a Face Anti-Spoofing System, focusing on leveraging the PyWavelets Library to compute Complex Wavelets for Face Images. Engineered a Multiscale Energy computation pipeline to analyze and differentiate between Original and Fake Face Images.Applied a range of Supervised Learning Models and implemented advanced ANN and CNN Models, including VGG-16 and AlexNet. Achieved a notable 87% accuracy in distinguishing between Genuine and Spoofed Face Images by employing the Random Forest Algorithm.The experience gained in this project sets the stage for future innovations in biometric security systems. The acquired insights can be leveraged to refine anti-spoofing algorithms and develop more sophisticated models for enhanced security applications.

Collaborated with a team of 2 members and worked under Scientist Deepak Kumar Verma. The project is focused on analyzing the effectiveness of various machine learning models in detecting network attacks on different protocols, such as TCPand UDP. Rigorously assessed and compared the accuracy of multiple Supervised Learning Algorithms in detecting network attacks on different protocols. Demonstrated the efficacy of the employed methodologies through empirical analysis and evaluation.Achieved a notable accuracy rate of 74% utilizing the Random Forest Algorithm for network attack detection.The successful outcomes of this project lay the foundation for further research and development in the field of network security. The insights gained can be utilized to refine existing detection systems and develop more robust models for safeguarding network infrastructure.