Venus-DefakerOne2: A Vision-Forensics Foundation Model with Broader Coverage

Hugging Face Daily Papers Papers
vision-forensics deepfake-detection foundation-model lora fine-tuning ai-generated-content

Summary

Venus-DefakerOne2 is a unified anti-forgery vision foundation model that broadens detection across forgery forms (digital manipulation, physical spoofs) and media types (images, videos) using Tide-Style-Tuning and entropy-based test adaptation, achieving state-of-the-art results on multiple forensic benchmarks.

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.
Original Article
View Cached Full Text

Cached at: 11/02/26, 11:28 AM

Paper page - Venus-DefakerOne2: A Vision-Forensics Foundation Model with Broader Coverage

Source: https://huggingface.co/papers/2610.37918 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-forgeryfoundation modelcovering 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 alternatesLoRAandfull-parameter fine-tuningto balance computational efficiency, generalization, and hard-sample fitting while mitigatingcatastrophic forgetting.Entropy-based Test Adaptationdetermines 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 versatilefoundation modelfor binary-decision forensic tasks.

View arXiv pageView PDFProject pageGitHub24Add 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

Models citing this paper1

#### qcf568/DefakerOne2 Updatedabout 18 hours ago • 1

Datasets citing this paper0

No dataset linking this paper

Cite arxiv.org/abs/2610.37918 in a dataset README.md to link it from this page.

Spaces citing this paper1

Collections including this paper0

No Collection including this paper

Add this paper to acollectionto link it from this page.

Similar Articles

AV-FABLE: Audio-Visual Manipulation Forensics in Long-Form Videos

Hugging Face Daily Papers

AV-FABLE introduces a long-form audio-visual benchmark for sparse manipulation detection, showing that frozen AV-LLM perception features contain forensic signals best recovered by separate temporal decoders (NFSR) rather than language outputs.

Multi-Agent Forensic Reasoning for Generalizable Deepfake Video Detection

Hugging Face Daily Papers

This paper introduces FaceVid-Forensics-100K, a large-scale deepfake video dataset with fine-grained annotations, and proposes a multi-agent forensic reasoning framework (ARGUS) that uses four specialized expert agents and a judge agent to outperform closed-source models on deepfake detection.

From Cheap Fakes to Pure Synthesis: Addressing the New Era of T2V Fake News Videos

arXiv cs.AI

This paper addresses the growing threat of pure-synthesis fake news videos generated by text-to-video models, introducing a new ternary classification task and the first pure-synthesis fake news video dataset (PS-FNVD), along with a Reasoning-guided framework (R-T2V) that achieves state-of-the-art detection accuracy.

Certification of Real Images through Calibrated Content Authentication

Hugging Face Daily Papers

The paper evaluates twenty deepfake detectors against ten generators, finding detection accuracy degrading from 99.5% to 76% over time and collapsing below 2% under adversarial perturbations, then proposes a calibrated detection paradigm based on plausibly deniable authenticity via generator reconstruction, achieving at most 1% false certification.