VGG16 在假图检测中达 91% 准确率，四模型对比研究
Comparative Evaluation of Deep Learning Models for Fake Image Detection
数字取证和内容安全团队需要知道哪个模型最靠谱——VGG16 以 91% 准确率胜出，但 EfficientNetB0 对假图更敏感，做检测系统的开发者可以直接参考这个基准来选型。
这项研究比较了 VGG16、ResNet50、EfficientNetB0 和 XceptionNet 四种预训练 CNN 模型在假图像检测上的表现。
在统一预处理和训练流程下，VGG16 以 91% 的准确率领先，其他三个模型均达到 90%。EfficientNetB0 对假图更敏感，但对真实样本可靠性较低，反映了数据集不平衡导致的偏差。
研究指出了数据集不平衡、过拟合和可解释性有限等限制，为开发更可靠的假图检测系统提供了可复现的基准。
Comparative Evaluation of Deep Learning Models for Fake Image Detection
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.
This report is categorized under AITOP's "Papers" desk. Key entities and technical topics under continuous tracking include 假图检测, CNN模型, VGG16, 数字取证.
Source attribution: curated from arXiv cs.AI (@Akhitha Pakala, Mohammed Mahir Rahman, Shahzad Memon, Tauseef Ahmed).