Detecting deepfakes has become an important task. Most existing detection methods provide only real/fake predictions without offering human-comprehensible explanations. Recent studies leveraging MLLMs for deepfake detection have shown improvements in explainability. However, the performance of pre-trained MLLMs (e.g., LLaVA) remains limited due to a lack of understanding of their capabilities for this task and strategies to enhance them. In this work, we empirically assess the strengths and weaknesses of MLLMs specifically in deepfake detection via forgery features analysis. Building on these assessments, we propose a novel framework called ${X}^2$-DFD, consisting of three core modules. The first module, Model Feature Assessment (MFA), measures the detection capabilities of forgery features intrinsic to MLLMs, and gives a descending ranking of these features. The second module, Strong Feature Strengthening (SFS), enhances the detection and explanation capabilities by fine-tuning the MLLM on a dataset constructed based on the top-ranked features. The third module, Weak Feature Supplementing (WFS), improves the fine-tuned MLLM's capabilities on lower-ranked features by integrating external dedicated deepfake detectors. To verify the effectiveness of this framework, we further present a practical implementation, where an automated forgery features generation, evaluation, and ranking procedure is designed for MFA module; an automated generation procedure of the fine-tuning dataset containing real and fake images with explanations based on top-ranked features is developed for SFS model; an external conventional deepfake detector focusing on blending artifact, which corresponds to a low detection capability in the pre-trained MLLM, is integrated for WFS module. Experiments show that our approach enhances both detection and explanation performance.

翻译：深度伪造检测已成为一项重要任务。现有的大多数检测方法仅提供真实/伪造的预测，而未能给出人类可理解的解释。近期利用多模态大语言模型（MLLMs）进行深度伪造检测的研究在可解释性方面已显示出改进。然而，由于缺乏对此任务中模型能力的理解以及相应的增强策略，预训练MLLMs（例如LLaVA）的性能仍然有限。在本工作中，我们通过伪造特征分析，实证评估了MLLMs在深度伪造检测任务中的优势与不足。基于这些评估，我们提出了一个名为X²-DFD的新框架，该框架包含三个核心模块。第一个模块是模型特征评估（MFA），用于衡量MLLMs内在的伪造特征检测能力，并对这些特征进行降序排名。第二个模块是强特征增强（SFS），通过基于排名靠前的特征构建的数据集对MLLM进行微调，以提升其检测与解释能力。第三个模块是弱特征补充（WFS），通过集成外部专用的深度伪造检测器，提升微调后MLLM对排名较低特征的检测能力。为验证该框架的有效性，我们进一步提出了一套具体实施方案：为MFA模块设计了自动化的伪造特征生成、评估与排序流程；为SFS模块开发了基于排名靠前特征、包含真实与伪造图像及其解释的微调数据集自动生成流程；为WFS模块集成了一个专注于融合伪影（对应于预训练MLLM中检测能力较低的特征）的外部传统深度伪造检测器。实验表明，我们的方法同时提升了检测性能与解释能力。