Omni-Fake：统一多模态社交媒体深度伪造检测基准
Omni-Fake: Benchmarking Unified Multimodal Social Media Deepfake Detection
提供了百万级图像/音频/视频/音视频说话人头的多模态伪造数据集与OOD基准，并给出三元检测（真实/部分篡改/全合成）加空间或时序定位掩码的评测协议，可直接用于训练和评测视觉伪造检测与篡改定位模型；Omni-Fake-R1 的强化学习驱动多模态检测器输出结构化决策与自然语言解释，为可解释伪造检测提供可复用范式。
原文依据 we define a ternary task (real / partially manipulated / fully synthetic) with spatial or temporal localization masks for fine-grained reasoning
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论在社交媒体上泛滥的多模态深度伪造威胁着真实性、信息完整性与数字取证。现有基准受限于单一模态范围、简化的篡改方式或不真实的分布，限制了其评估真实世界鲁棒性的能力。我们提出 Omni-Fake，一个用于社交媒体场景下全面多模态深度伪造检测的统一全数据集。它包含 Omni-Fake-Set——一个含 100 万以上样本的大规模高质量数据集，以及 Omni-Fake-OOD——一个含 10 万以上样本、被有意排除在训练之外以评估泛化性的分布外基准。Omni-Fake 覆盖四种模态——图像、音频、视频以及音视频说话人头，并支持联合的检测-定位-解释协议。对于图像、音频和视频，我们定义了一个三元任务（真实/部分篡改/全合成），并配有空间或时序定位掩码以支持细粒度推理。说话人头被形式化为一个音视频融合的二分类任务，针对说话的数字人和唇形同步的虚拟形象伪造。在 Omni-Fake 之上，我们进一步提出 Omni-Fake-R1，一个由强化学习驱动的多模态检测器，能够自适应地整合视觉与听觉线索，并输出结构化决策、定位与自然语言解释。大量实验表明，其在检测准确率、跨模态泛化性和可解释性上相较最优基线取得显著提升。代码将开源。
英文原文摘要 1510 字符
Multimodal Deepfakes proliferating on social media threaten authenticity, information integrity, and digital forensics. Existing benchmarks are constrained by their single-modality scope, simplified manipulations, or unrealistic distributions, which limit their ability to assess real-world robustness. We present Omni-Fake, a unified omni-dataset for comprehensive multimodal deepfake detection in social-media settings. It comprises Omni-Fake-Set, a large-scale, high-quality dataset with 1M+ samples, and Omni-Fake-OOD, an out-of-distribution benchmark with 100k+ samples intentionally excluded from training to evaluate generalization. Omni-Fake spans four modalities--image, audio, video, and audio-video talking head and supports a joint detection-localization-explanation protocol. For images, audio, and videos, we define a ternary task (real / partially manipulated / fully synthetic) with spatial or temporal localization masks for fine-grained reasoning. Talking heads are formulated as an audio-video fusion binary task targeting speaking digital humans and lip-synced avatar forgeries. On top of Omni-Fake, we further propose Omni-Fake-R1, a reinforcement-learning-driven multimodal detector that adaptively integrates visual and auditory cues and outputs structured decisions, localization, and natural-language explanations. Extensive experiments show significant gains in detection accuracy, cross-modal generalization, and explainability over state-of-the-art baselines. Code will be released.