A Decade of Multiple-media Forgery Detection: A Comprehensive Review

Abstract

The rapid proliferation of digital media and ease of manipulation necessitate ro- bust forgery detection techniques to maintain multimedia trustworthiness. This review paper offers a comprehensive overview of the advancements in forgery detection techniques over the past decade, focusing on traditional, machine learn- ing-based, and deep learning-based approaches. Traditional techniques involve watermarking, signatures, and statistical property analysis, while machine learn- ing-based methods employ supervised learning for automatic forgery classifica- tion. Deep learning-based methods utilize convolutional neural networks (CNNs) to learn hierarchical features from raw pixel data, demonstrating exceptional per- formance in detecting advanced manipulations. Despite these advancements, challenges persist, including limited availability of labeled data, adversarial at- tacks, generalization across different forgery techniques, and real-time detection. Addressing these challenges is crucial for enhancing the trustworthiness of digital media and preserving the integrity of the digital landscape. This review paper aims to provide a thorough understanding of the current state of multiple-media forgery detection and inspire future research directions to tackle remaining chal- lenges.