Content-Driven Multimodal Deepfake Generation and Temporal Localization

This thesis investigates the challenges and advances in detecting sophisticated video manipulations named content-driven deepfakes, where slight, strategic changes can drastically alter the video's meaning. Focusing on the content-driven deepfakes not well-addressed by current detection methods, this research introduces new datasets and detection approaches for precisely localizing these manipulations. This thesis contributes valuable tools and insights for addressing deepfake threats, highlighting the importance of reliable detection in maintaining media integrity and security.