DFDC
The Deepfake Detection Challenge, a large-scale competition and accompanying dataset initiated by Facebook (Meta). The dataset encompasses diverse forgery methods and reflects the distribution characteristics of real social-media content, making it one of the benchmarks most closely aligned with real-world deepfake detection scenarios.
Timeline (last 90 days)
In-the-wild benchmarks such as DFDC (Deepfake Detection Challenge) and DeeperForensics are closer to real dissemination scenarios on social media and video platforms than the earlier laboratory dataset FaceForensics++.
AI video generation model training relies on large-scale facial action datasets such as DFDC and FaceForensics++.
All Facts (3)
Meta、微软等科技巨头联合学术机构发起了Deepfake Detection Challenge（DFDC）竞赛，推动深度伪造检测模型的快速迭代
90%UnverifiedIn-the-wild benchmarks such as DFDC (Deepfake Detection Challenge) and DeeperForensics are closer to real dissemination scenarios on social media and video platforms than the earlier laboratory dataset FaceForensics++.
50%UnverifiedAI video generation model training relies on large-scale facial action datasets such as DFDC and FaceForensics++.
50%