当前位置: X-MOL 学术IEEE Trans. Inform. Forensics Secur. › 论文详情
Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)
Masked Relation Learning for DeepFake Detection
IEEE Transactions on Information Forensics and Security ( IF 6.3 ) Pub Date : 2-27-2023 , DOI: 10.1109/tifs.2023.3249566
Ziming Yang 1 , Jian Liang 2 , Yuting Xu 2 , Xiao-Yu Zhang 1 , Ran He 2
Affiliation  

DeepFake detection aims to differentiate falsified faces from real ones. Most approaches formulate it as a binary classification problem by solely mining the local artifacts and inconsistencies of face forgery, which neglect the relation across local regions. Although several recent works explore local relation learning for DeepFake detection, they overlook the propagation of relational information and lead to limited performance gains. To address these issues, this paper provides a new perspective by formulating DeepFake detection as a graph classification problem, in which each facial region corresponds to a vertex. But relational information with large redundancy hinders the expressiveness of graphs. Inspired by the success of masked modeling, we propose Masked Relation Learning which decreases the redundancy to learn informative relational features. Specifically, a spatiotemporal attention module is exploited to learn the attention features of multiple facial regions. A relation learning module masks partial correlations between regions to reduce redundancy and then propagates the relational information across regions to capture the irregularity from a global view of the graph. We empirically discover that a moderate masking rate (e.g., 50%) brings the best performance gain. Experiments verify the effectiveness of Masked Relation Learning and demonstrate that our approach outperforms the state of the art by 2% AUC on the cross-dataset DeepFake video detection. Code will be available at https://github.com/zimyang/MaskRelation.

中文翻译:


用于 DeepFake 检测的屏蔽关系学习



DeepFake 检测旨在区分伪造的面孔和真实的面孔。大多数方法通过仅挖掘局部伪影和人脸伪造的不一致性,将其表述为二元分类问题,而忽略了局部区域之间的关系。尽管最近的几项工作探索了用于 DeepFake 检测的局部关系学习,但它们忽视了关系信息的传播并导致性能提升有限。为了解决这些问题,本文提供了一个新的视角,将 DeepFake 检测制定为图分类问题,其中每个面部区域对应一个顶点。但冗余度大的关系信息阻碍了图的表达能力。受屏蔽建模成功的启发,我们提出了屏蔽关系学习,它减少了学习信息关系特征的冗余。具体来说,利用时空注意力模块来学习多个面部区域的注意力特征。关系学习模块屏蔽区域之间的部分相关性以减少冗余,然后跨区域传播关系信息以从图形的全局视图中捕获不规则性。我们凭经验发现,适度的掩蔽率(例如 50%)可以带来最佳的性能增益。实验验证了掩蔽关系学习的有效性,并证明我们的方法在跨数据集 DeepFake 视频检测上的 AUC 比现有技术高出 2%。代码可在 https://github.com/zimyang/MaskRelation 获取。
更新日期:2024-08-26
down
wechat
bug