DevFD：通过学习共享与正交 LoRA 子空间实现发展式人脸伪造检测
DevFD: Developmental Face Forgery Detection by Learning Shared and Orthogonal LoRA Subspaces
AI总结：
本文提出发展式人脸伪造检测方法 DevFD，以持续学习应对不断演化的伪造类型，通过 Real-LoRA 与多个正交 Fake-LoRA 的专家混合架构在适应新伪造的同时避免遗忘旧知识。
摘要：
逼真数字人脸生成与操纵技术的兴起带来了显著的社会风险。主要挑战在于生成技术的快速且多样化演进，往往超出已有模型的检测能力。为了防御不断出现的新型伪造，我们需要使模型能够在有限的计算和数据条件下快速适应新领域，同时避免遗忘先前学到的伪造类型。本文认为，真实人脸样本数量充足且获取方式相对稳定，而伪造人脸则随着操纵技术的迭代不断演化。鉴于穷尽收集所有伪造变体在实际中不可行，我们将人脸伪造检测构建为一个持续学习问题，并允许模型随着新型伪造类型的出现而不断发展。具体而言，我们采用一种发展式专家混合（MoE）架构，以 LoRA 模型作为其各个专家。这些专家被组织为两组：一个 Real-LoRA 用于学习和精炼真实人脸知识，多个 Fake-LoRA 用于捕获不同伪造类型的增量信息。为防止灾难性遗忘，我们确保 Fake-LoRA 的学习方向与已建立子空间正交。此外，我们将正交梯度整合到 Fake-LoRA 的正交损失中，从而在每个任务的整个训练过程中防止梯度干扰。在数据集和操纵类型增量协议下的实验结果证明了我们方法的有效性。
英文摘要：
The rise of realistic digital face generation and manipulation poses significant social risks. The primary challenge lies in the rapid and diverse evolution of generation techniques, which often outstrip the detection capabilities of existing models. To defend against the ever-evolving new types of forgery, we need to enable our model to quickly adapt to new domains with limited computation and data while avoiding forgetting previously learned forgery types. In this work, we posit that genuine facial samples are abundant and relatively stable in acquisition methods, while forgery faces continuously evolve with the iteration of manipulation techniques. Given the practical infeasibility of exhaustively collecting all forgery variants, we frame face forgery detection as a continual learning problem and allow the model to develop as new forgery types emerge. Specifically, we employ a Developmental Mixture of Experts (MoE) architecture that uses LoRA models as its individual experts. These experts are organized into two groups: a Real-LoRA to learn and refine knowledge of real faces, and multiple Fake-LoRAs to capture incremental information from different forgery types. To prevent catastrophic forgetting, we ensure that the learning direction of Fake-LoRAs is orthogonal to the established subspace. Moreover, we integrate orthogonal gradients into the orthogonal loss of Fake-LoRAs, preventing gradient interference throughout the training process of each task. Experimental results under both the datasets and manipulation types incremental protocols demonstrate the effectiveness of our method.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
