Venus-DefakerOne2：一个覆盖范围更广的视觉取证基础模型

Published on Oct 27

Authors:

Abstract

Venus-DefakerOne2 is a unified anti-forgery foundation model that extends detection to diverse forgery forms and media types through alternating LoRA and full-parameter tuning and entropy-based test adaptation.

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.

View arXiv page View PDF Project page GitHub 24 Add to collection

Get this paper in your agent:

hf papers read 2610.37918

Don't have the latest CLI?

curl -LsSf https://hf.co/cli/install.sh | bash