一个模型，六种造假，全抓
造假不是一种病：有人用 AI 换脸，有人伪造证件，有人生成假视频，还有人物理上拿张照片骗过人脸识别。过去每个领域都得养一个专门的检测模型，换一种造假就得换一个工具。这篇把六类造假——AI 换脸、AI 生成图、篡改文档、篡改自然图、物理欺骗、AI 视频——塞进同一个模型，在千万级样本上训练，六项基准全部刷新纪录，最高 96.7%。它不是你明天能装进 App 的现成方案，但它是「造假检测从单科专家走向全科医生」的信号：以后平台审核、取证工具可能不再需要堆一堆模型，一个就够了。
📄 原文摘要(英文)
Real-world forgery is inherently heterogeneous: it manifests not only as digital manipulation but also as physical spoofing, and is carried not only by images but also by videos. Despite substantial progress, a unified anti-forgery foundation model covering such a broad threat spectrum remains absent. In this paper, we present Venus-DefakerOne2, which substantially extends the forensic capability boundary along both the forgery-form and media-type dimensions. Trained on tens of millions of open-source and in-house samples, it incorporates two key designs. Tide-Style-Tuning alternates LoRA and full-parameter fine-tuning to balance computational efficiency, generalization, and hard-sample fitting while mitigating catastrophic forgetting. Entropy-based Test Adaptation determines the optimal prediction modality by analyzing prediction entropy. Venus-DefakerOne2 achieves new state-of-the-art performance across a comprehensive suite of benchmarks, including DeepFake faces (96.7%), AI-generated images (93.3%), tampered documents (87.6%), manipulated natural images (89.6%), physical spoofs (93.1%), and AI-generated videos (96.0%). It significantly outperforms both specialized expert models and its predecessor, DefakerOne, establishing itself as a powerful and versatile foundation model for binary-decision forensic tasks.