@inproceedings{6ad418763f0a4e1ba593e69c982ce9b6,
title = "Integrating Audio-Visual Features for Multimodal Deepfake Detection",
abstract = "Deepfakes are AI-generated media in which an image or video has been digitally modified. The advancements made in deepfake technology have led to privacy and security issues. Most deepfake detection techniques rely on the detection of a single modality. Existing methods for audio-visual detection do not always surpass that of the analysis based on single modalities. Therefore, this paper proposes an audio visual based method for deepfake detection, which integrates fine-grained deepfake identification with binary classification. We categorize the samples into four types by combining labels specific to each single modality. This method enhances the detection under intra-domain and cross-domain testing.",
keywords = "Audio-visual feature learning, Deepfake detection, Multi-modality deepfakes",
author = "Sneha Muppalla and Shan Jia and Siwei Lyu",
note = "Publisher Copyright: {\textcopyright} 2023 IEEE.; 2023 IEEE MIT Undergraduate Research Technology Conference, URTC 2023 ; Conference date: 06-10-2023 Through 08-10-2023",
year = "2023",
doi = "10.1109/URTC60662.2023.10534969",
language = "English",
series = "IEEE MIT Undergraduate Research Technology Conference, URTC 2023 - Proceedings",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
booktitle = "IEEE MIT Undergraduate Research Technology Conference, URTC 2023 - Proceedings",
address = "United States",
}