TI2Net: Temporal Identity Inconsistency Network for Deepfake Detection

Baoping Liu, Bo Liu, Ming Ding, Tianqing Zhu, Xin Yu; Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV), 2023, pp. 4691-4700

Abstract


In this paper, we propose a Temporal Identity Inconsistency Network (TI2Net), a Deepfake detector that focuses on temporal identity inconsistency. Specifically, TI2Net recognizes fake videos by capturing the dissimilarities of human faces among video frames of the same identity. Therefore, TI2Net is a reference-agnostic detector and can be used on unseen datasets. For a video clip of a given identity, identity information in all frames will first be encoded to identity vectors. TI2Net learns the temporal identity embedding from the temporal difference of the identity vectors. The temporal embedding, representing the identity inconsistency in the video clip, is finally used to determine the authenticity of the video clip. During training, TI2Net incorporates triplet loss to learn more discriminative temporal embeddings. We conduct comprehensive experiments to evaluate the performance of the proposed TI2Net. Experimental results indicate that TI2Net generalizes well to unseen manipulations and datasets with unseen identities. Besides, TI2Net also shows robust performance against compression and additive noise.

Related Material


[pdf] [supp]
[bibtex]
@InProceedings{Liu_2023_WACV, author = {Liu, Baoping and Liu, Bo and Ding, Ming and Zhu, Tianqing and Yu, Xin}, title = {TI2Net: Temporal Identity Inconsistency Network for Deepfake Detection}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2023}, pages = {4691-4700} }