IVT-Guard：面向AI生成内容检测的全能推理模型
IVT-Guard: All-in-One Reasoning Model for AI-Generated Content Detection
- Xiamen University（厦门大学）
- Tencent YouTu Lab（腾讯优图实验室）
机构由 AI 辅助整理，请以论文原文为准。
AI总结：
针对现有AIGC检测局限于单模态且缺乏推理的问题，本文提出IVT-Guard框架，结合IVT-Set数据集和三阶段训练范式，实现跨图像、视频、文本的统一可解释检测，并达到最先进性能。
AI中文摘要：
高度逼真的AI生成内容（AIGC）的快速激增，迫切需要稳健且可解释的检测机制。然而，现有检测器主要局限于单一模态，并提供无推理的二元输出。尽管多模态大语言模型（MLLMs）提供了一个有前景的解决方案，但其发展受到多模态推理数据稀缺和推理-检测优化困境的制约，其中显式推理监督可能损害检测准确性。为此，我们引入了IVT-Set，一个包含超过15.2万个多样化的图像、视频和文本样本的综合数据集，并配备了多粒度思维链（CoT）推理轨迹。基于此，我们提出了IVT-Guard，一个用于跨图像、视频和文本模态的统一且可解释的AIGC检测的开创性框架。此外，为克服上述优化困境，我们设计了一种新颖的三阶段训练范式：伪影感知预训练、通过伪影感知注入的伪影到证据监督微调，以及证据-裁决一致性组相对策略优化。大量实验表明，IVT-Guard在域内、域外和跨数据集设置中均实现了最先进的检测性能，同时提供了忠实的推理。代码和数据将公开发布。
英文摘要：
The rapid proliferation of highly realistic AI-Generated Content (AIGC) necessitates robust and interpretable detection mechanisms. However, existing detectors are predominantly confined to single modalities and provide binary outputs without reasoning. While Multimodal Large Language Models (MLLMs) present a promising solution, their development is constrained by the scarcity of multimodal reasoning data and the reasoning-detection optimization dilemma, where explicit reasoning supervision can compromise detection accuracy. To this end, we introduce IVT-Set, a comprehensive dataset comprising over 152K diverse image, video, and text samples equipped with multi-granularity Chain-of-Thought (CoT) reasoning trajectories. Based on it, we propose IVT-Guard, a pioneering framework for unified and interpretable AIGC detection across image, video, and text modalities. Furthermore, to overcome the aforementioned optimization dilemma, we design a novel three-stage training paradigm: Artifact-Aware Pre-training, Artifact-to-Evidence Supervised Fine-Tuning via artifact-aware injection, and Evidence-Verdict Consistency Group Relative Policy Optimization. Extensive experiments demonstrate that IVT-Guard achieves state-of-the-art detection performance across in-domain, out-of-domain, and cross-dataset settings while delivering faithful reasoning. Code and data will be released.
