Recent deefake detection models mainly use binary classification models based on deep learning. Despite achieving high detection accuracy on intra-dataset, these models lack generalization ability when applied to cross-datasets. We propose a deepfake detection model named Channel-Spatial-Triplet Attention Network (CSTAN), which focuses on the difference between real and fake features, thereby enhancing the generality of detection model. To enhance the feature learning ability of the model for image forgery regions, we design Channel-Spatial-Triplet (CST) attention mechanism, which extracts subtle local information by capturing feature channels and spatial correlation of three different scales. Additionally, we propose a novel feature extraction method OD-ResNet-34 by embedding ODConv into the feature extraction network to enhance its dynamic adaptability to data features. Trained on the FF++ dataset and tested on the Celeb-DF-v1 and Celeb-DF-v2 datasets, the experimental results show that our model has stronger generalization ability in cross-dataset than similar model.