Published Paper Details:

The proliferation of deepfake technology poses significant challenges to the integrity of digital content, necessitating robust detection mechanisms. In this study, we propose a hybrid approach that integrates ResNet, a convolutional neural network (CNN) architecture known for its feature extraction capabilities, with Long Short-Term Memory (LSTM) networks, specialized in capturing temporal dependencies. Our method aims to enhance the accuracy and effectiveness of deepfake detection by combining spatial and temporal information within a unified framework. We curate a diverse dataset containing authentic and deepfake videos, preprocess the data, and train the hybrid model using deep learning techniques. Evaluation on a separate test dataset demonstrates the superior performance of our approach, achieving high accuracy and precision in distinguishing between authentic and deepfake videos. Comparative analysis with baseline methods further validates the effectiveness of the proposed approach. Additionally, ethical considerations are carefully addressed throughout the research process, ensuring responsible development and deployment of the deepfake detection system. Through this study, we contribute to the advancement of techniques for combating deceptive visual media and preserving trust in digital content.