Ensemble Approach for Image Recompression-Based Forgery Detection

In today’s digital age, images are vulnerable to manipulation for malicious purposes such as spreading fake news, prompting active research in image forgery detection. With the advances in deep learning (DL), convolutional neural network (CNN) and Transformer models have emerged as prominent tools in this field. However, individual models may excel with certain images while performing poorly with others, leading to variability in model performance. To address this issue, this paper proposes an ensemble approach that combines predictions from multiple models to improve system performance and robustness. First, we utilize a set of pretrained DL models, including CNN-based models, Transformer-based models, and fusion models that combine these architectures, and select the best-performing models. Then, these selected models are employed in an ensemble approach using hard voting and soft voting to evaluate their collective performance. Notably, among the selected ensemble of ConvNeXt, SwinV2, and CAFormer, the hard voting technique achieves an accuracy of 97.42%, which is approximately a 6.34% improvement over the baseline model. This result confirms the effectiveness of the proposed ensemble approach for forgery detection.