Manipulated Face Detection System Using Deep Learning

– In this research, we propose a novel approach for detecting and explaining deepfake images using deep learning techniques. Our method utilizes a combination of face detection, feature extraction, and attention visualization to provide insights into the authenticity of facial images. We employ the Multi-Task Cascaded Convolutional Neural Network (MTCNN) for accurate face detection and the InceptionResnetV1 architecture pretrained on the VGGFace2 dataset for feature extraction. The model is further enhanced with GradCAM, a gradient-based visualization technique, to highlight the regions of the input image contributing most to the classification decision. Our approach offers interpretable explanations by overlaying attention maps onto the original images, enabling users to understand the model’s decision-making process. Experimental results demonstrate the effectiveness and interpretability of our method in detecting deepfake images and providing insightful explanations, contributing to the advancement of deepfake detection research.