Do You Really Mean That? Content Driven Audio-Visual Deepfake Dataset and Multimodal Method for Temporal Forgery Localization
This addresses the challenge of sophisticated deepfakes that manipulate small segments to change content meaning, which is important for media integrity and security, though it is incremental as it builds on existing deepfake detection methods.
The authors tackled the problem of detecting localized deepfake manipulations that alter content meaning, such as sentiment polarity, by introducing a new dataset (LAV-DF) and a baseline method (BA-TFD) that achieved strong performance in temporal forgery localization and deepfake detection.
Due to its high societal impact, deepfake detection is getting active attention in the computer vision community. Most deepfake detection methods rely on identity, facial attributes, and adversarial perturbation-based spatio-temporal modifications at the whole video or random locations while keeping the meaning of the content intact. However, a sophisticated deepfake may contain only a small segment of video/audio manipulation, through which the meaning of the content can be, for example, completely inverted from a sentiment perspective. We introduce a content-driven audio-visual deepfake dataset, termed Localized Audio Visual DeepFake (LAV-DF), explicitly designed for the task of learning temporal forgery localization. Specifically, the content-driven audio-visual manipulations are performed strategically to change the sentiment polarity of the whole video. Our baseline method for benchmarking the proposed dataset is a 3DCNN model, termed as Boundary Aware Temporal Forgery Detection (BA-TFD), which is guided via contrastive, boundary matching, and frame classification loss functions. Our extensive quantitative and qualitative analysis demonstrates the proposed method's strong performance for temporal forgery localization and deepfake detection tasks.