Glitch in the matrix: A large scale benchmark for content driven audio–visual forgery detection and localization

Zhixi Cai, Shreya Ghosh, Abhinav Dhall, Tom Gedeon, Kalin Stefanov, Munawar Hayat

Research output: Contribution to journalArticlepeer-review

10 Citations (Scopus)
19 Downloads (Pure)

Abstract

Most deepfake detection methods focus on detecting spatial and/or spatio-temporal changes in facial attributes and are centered around the binary classification task of detecting whether a video is real or fake. This is because available benchmark datasets contain mostly visual-only modifications present in the entirety of the video. However, a sophisticated deepfake may include small segments of audio or audio–visual manipulations that can completely change the meaning of the video content. To addresses this gap, we propose and benchmark a new dataset, Localized Audio Visual DeepFake (LAV-DF), consisting of strategic content-driven audio, visual and audio–visual manipulations. The proposed baseline method, Boundary Aware Temporal Forgery Detection (BA-TFD), is a 3D Convolutional Neural Network-based architecture which effectively captures multimodal manipulations. We further improve (i.e. BA-TFD+) the baseline method by replacing the backbone with a Multiscale Vision Transformer and guide the training process with contrastive, frame classification, boundary matching and multimodal boundary matching loss functions. The quantitative analysis demonstrates the superiority of BA-TFD+ on temporal forgery localization and deepfake detection tasks using several benchmark datasets including our newly proposed dataset. The dataset, models and code are available at https://github.com/ControlNet/LAV-DF.

Original languageEnglish
Article number103818
Number of pages12
JournalComputer Vision and Image Understanding
Volume236
Early online date23 Aug 2023
DOIs
Publication statusPublished - Nov 2023
Externally publishedYes

Keywords

  • Datasets
  • Deepfake
  • Detection
  • Localization

Fingerprint

Dive into the research topics of 'Glitch in the matrix: A large scale benchmark for content driven audio–visual forgery detection and localization'. Together they form a unique fingerprint.

Cite this