Multimodal Graph Learning for Deepfake Detection
Existing deepfake detectors face several challenges in achieving robustness and generalization. One of the primary reasons is their limited ability to extract relevant information from forgery videos, especially in the presence of various artifacts such as spatial, frequency, temporal, and landmark mismatches. Current detectors rely on pixel-level features that are easily affected by unknown disturbances or facial landmarks that do not provide sufficient information. Furthermore, most detectors cannot utilize information from multiple domains for detection, leading to limited effectiveness in identifying deepfake videos. To address these limitations, we propose a novel framework, namely Multimodal Graph Learning (MGL) that leverages information from multiple modalities using two GNNs and several multimodal fusion modules. At the frame level, we employ a bi-directional cross-modal transformer and an adaptive gating mechanism to combine the features from the spatial and frequency domains with the geometric-enhanced landmark features captured by a GNN. At the video level, we use a Graph Attention Network (GAT) to represent each frame in a video as a node in a graph and encode temporal information into the edges of the graph to extract temporal inconsistency between frames. Our proposed method aims to effectively identify and utilize distinguishing features for deepfake detection. We evaluate the effectiveness of our method through extensive experiments on widely-used benchmarks and demonstrate that our method outperforms the state-of-the-art detectors in terms of generalization ability and robustness against unknown disturbances.
Code (0)
등록된 구현이 없습니다.
Tasks
DeepFake DetectionFace SwappingGraph AttentionGraph LearningSimilar Papers 제목 키워드 기반
PRPO: Paragraph-level Policy Optimization for Vision-Language Deepfake Detection
The rapid rise of synthetic media has made deepfake detection a critical challenge for online safety and trust. Progress remains constrained by the scarcity of large, high-quality datasets. Although multimodal large lang…
Reinforcement LearningMultimodal ReasoningDeepFake DetectionPolyGlotFake: A Novel Multilingual and Multimodal DeepFake Dataset
With the rapid advancement of generative AI, multimodal deepfakes, which manipulate both audio and visual modalities, have drawn increasing public concern. Currently, deepfake detection has emerged as a crucial strategy …
DeepFake DetectionFace Swappingtext-to-speechText to Speech+1KLASSify to Verify: Audio-Visual Deepfake Detection Using SSL-based Audio and Handcrafted Visual Features
The rapid development of audio-driven talking head generators and advanced Text-To-Speech (TTS) models has led to more sophisticated temporal deepfakes. These advances highlight the need for robust methods capable of det…
Self-Supervised LearningDeepFake DetectionDeepfakeBench-MM: A Comprehensive Benchmark for Multimodal Deepfake Detection
The misuse of advanced generative AI models has resulted in the widespread proliferation of falsified data, particularly forged human-centric audiovisual content, which poses substantial societal risks (e.g., financial f…
DeepFake DetectionMIS-AVoiDD: Modality Invariant and Specific Representation for Audio-Visual Deepfake Detection
Deepfakes are synthetic media generated using deep generative algorithms and have posed a severe societal and political threat. Apart from facial manipulation and synthetic voice, recently, a novel kind of deepfakes has …
DeepFake DetectionFace Swapping