Comparative Evaluation of Deep Learning Models for Fake Image Detection
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2026
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866911701169864704 |
|---|---|
| author | Pakala, Akhitha Rahman, Mohammed Mahir Memon, Shahzad Ahmed, Tauseef |
| author_facet | Pakala, Akhitha Rahman, Mohammed Mahir Memon, Shahzad Ahmed, Tauseef |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2605_20971 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Comparative Evaluation of Deep Learning Models for Fake Image Detection Pakala, Akhitha Rahman, Mohammed Mahir Memon, Shahzad Ahmed, Tauseef Computer Vision and Pattern Recognition Artificial Intelligence Cryptography and Security 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. |
| title | Comparative Evaluation of Deep Learning Models for Fake Image Detection |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence Cryptography and Security |
| url | https://arxiv.org/abs/2605.20971 |