Straight Through Gumbel Softmax Estimator based Bimodal Neural Architecture Search for Audio-Visual Deepfake Detection
원문 초록
Deepfakes are a major security risk for biometric authentication. This technology creates realistic fake videos that can impersonate real people, fooling systems that rely on facial features and voice patterns for identification. Existing multimodal deepfake detectors rely on conventional fusion methods, such as majority rule and ensemble voting, which often struggle to adapt to changing data characteristics and complex patterns. In this paper, we introduce the Straight-through Gumbel-Softmax (STGS) framework, offering a comprehensive approach to search multimodal fusion model architectures. Using a two-level search approach, the framework optimizes the network architecture, parameters, and performance. Initially, crucial features were efficiently identified from backbone networks, whereas within the cell structure, a weighted fusion operation integrated information from various sources. An architecture that maximizes the classification performance is derived by varying parameters such as temperature and sampling time. The experimental results on the FakeAVCeleb and SWAN-DF datasets demonstrated an impressive AUC value 94.4\% achieved with minimal model parameters.
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
Pay Less Attention to Deceptive Artifacts: Robust Detection of Compressed Deepfakes on Online Social Networks
FAME: A Lightweight Spatio-Temporal Network for Model Attribution of Face-Swap Deepfakes
Unmasking real-world audio deepfakes: A data-centric approach
TADA: Training-free Attribution and Out-of-Domain Detection of Audio Deepfakes
Multiverse Through Deepfakes: The MultiFakeVerse Dataset of Person-Centric Visual and Conceptual Manipulations
Few-Shot Speech Deepfake Detection Adaptation with Gaussian Processes
토론
이 논문과 연결된 포럼 글이 아직 없습니다.