Comparative Evaluation of Deep Learning Models for Fake Image Detection
For digital forensics practitioners, this provides a reproducible baseline comparing standard CNN architectures on fake image detection, though the results are incremental.
This study compares four pretrained CNN models (VGG16, ResNet50, EfficientNetB0, XceptionNet) for fake image detection, finding VGG16 achieves the highest accuracy at 91%, while EfficientNetB0 shows stronger sensitivity to fakes but reduced reliability on real samples.
The growing sophistication of GAN-based image manipulation presents significant challenges for digital forensics. This study compares the performance of four pretrained CNN architectures including VGG16, ResNet50, EfficientNetB0, and XceptionNet for fake image detection using a unified preprocessing and training pipeline. A dataset of real and manipulated images was processed through resizing, normalization, and augmentation to address class imbalance and improve generalization. Models were evaluated using Accuracy, Precision, Recall, F1-score, and ROC-AUC. VGG16 achieved the highest accuracy at 91%, with XceptionNet, ResNet50, and EfficientNetB0 each reaching 90%. EfficientNetB0 showed stronger sensitivity to fake images but reduced reliability on real samples, reflecting imbalance-driven bias. Limitations include dataset imbalance, overfitting, and limited interpretability, which affect cross-domain robustness. The study provides a reproducible baseline and underscores the need for balanced datasets, advanced augmentation, and fairness-aware training to develop reliable fake image detection systems.