🤖 AI Summary
This study addresses the growing prevalence of digital image manipulation by proposing a hybrid input representation that integrates compression-based difference features (FDIFF) with RGB channels, leveraging a transfer learning framework to enhance forgery detection performance. Built upon pretrained CNN architectures—DenseNet121, ResNet50, and VGG16—the method incorporates a Youden index–driven adaptive thresholding strategy to optimally balance true positive and false positive rates. Experimental results on the CASIA v2.0 dataset demonstrate that the proposed approach significantly improves detection robustness and practicality: DenseNet121 achieves the highest accuracy and AUC, while ResNet50 yields the best Matthews Correlation Coefficient (MCC), collectively validating the efficacy of combining compression-aware features with adaptive threshold optimization.
📝 Abstract
The increasing availability of advanced image editing tools has led to a significant rise in manipulated digital content, posing serious challenges for digital forensics and information security. This study presents a transfer learning-based framework for digital image forgery detection that integrates compression-aware feature enhancement with deep convolutional neural network (CNN) architectures.
The proposed approach introduces a hybrid input representation that combines RGB images with compression difference-based features (FDIFF), explicitly highlighting subtle manipulation artifacts that are often difficult to detect. In addition, a model-specific adaptive threshold optimization strategy based on the Youden Index is employed to improve classification reliability by achieving a better balance between true positive and false positive rates.
Experiments conducted on the CASIA v2.0 dataset using multiple pretrained CNN architectures, including DenseNet121, VGG16, ResNet50, EfficientNetB0, MobileNet, and InceptionV3, demonstrate the effectiveness and robustness of the proposed framework. The models are evaluated using comprehensive performance metrics such as accuracy, precision, recall, F1-score, Matthews correlation coefficient (MCC), and area under the ROC curve (AUC).
The results show that DenseNet121 achieves the highest accuracy and AUC, while ResNet50 provides the most balanced and reliable predictions with the highest MCC. The findings emphasize that relying solely on accuracy is insufficient for forensic applications, where minimizing false negatives is critical. Overall, the proposed framework improves the visibility of manipulation artifacts and enhances classification robustness, making it suitable for real-world digital image forgery detection scenarios.