The malicious use and widespread dissemination of deepfake pose a significant crisis of trust. Current deepfake detection models can generally recognize forgery images by training on a large dataset. However, the accuracy of detection models degrades significantly on images generated by new deepfake methods due to the difference in data distribution. To tackle this issue, we present a novel incremental learning framework that improves the generalization of deepfake detection models by continual learning from a small number of new samples. To cope with different data distributions, we propose to learn a domain-invariant representation based on supervised contrastive learning, preventing overfit to the insufficient new data. To mitigate catastrophic forgetting, we regularize our model in both feature-level and label-level based on a multi-perspective knowledge distillation approach. Finally, we propose to select both central and hard representative samples to update the replay set, which is beneficial for both domain-invariant representation learning and rehearsal-based knowledge preserving. We conduct extensive experiments on four benchmark datasets, obtaining the new state-of-the-art average forgetting rate of 7.01 and average accuracy of 85.49 on FF++, DFDC-P, DFD, and CDF2. Our code is released at https://github.com/DeepFakeIL/DFIL.

翻译：深度伪造技术的恶意使用与广泛传播引发了严重的信任危机。现有深度伪造检测模型通常通过在海量数据集上训练来识别伪造图像。然而，由于数据分布差异，当检测模型面对新型深度伪造方法生成的图像时，其准确率会显著下降。为解决该问题，我们提出了一种新颖的增量学习框架，通过持续学习少量新样本来提升深度伪造检测模型的泛化能力。为应对不同数据分布，我们提出基于监督对比学习学习域不变表示，防止对新增数据不足的过拟合；为缓解灾难性遗忘，我们基于多视角知识蒸馏方法在特征层和标签层同时约束模型；最后，我们提出选择中心代表样本与困难代表样本更新回放集，这有助于域不变表示学习及基于回放的知识保留。我们在四个基准数据集上开展了大量实验，在FF++、DFDC-P、DFD和CDF2上分别实现了7.01的平均遗忘率和85.49的平均准确率，均达到当前最优水平。我们的代码已开源至https://github.com/DeepFakeIL/DFIL。