IVY-FAKE: A Unified Explainable Framework and Benchmark for Image and Video AIGC Detection

2025-06-01

AI Summary

Existing AIGC detection methods are predominantly opaque black-box binary classifiers lacking unified image-video modeling capabilities, thereby limiting transparency and practical applicability. To address this, we propose IVY-XDETECTOR—the first vision-language model enabling end-to-end, cross-modal (image/video) explainable detection. We further introduce IVY-FAKE, a large-scale explainable benchmark comprising over 150,000 samples with natural language inference-based attribution annotations. Our contributions are threefold: (1) a unified, explainable detection framework for both images and videos; (2) the first multimodal AIGC benchmark featuring fine-grained linguistic attribution; and (3) a novel architecture integrating cross-modal alignment, explainable attention mechanisms, and diffusion-artifact modeling to jointly produce detection outputs and human-readable attributions. IVY-XDETECTOR achieves state-of-the-art performance on both image and video detection benchmarks. The IVY-FAKE dataset and model are publicly released on Hugging Face.

Technology Category

• Computer Vision: Large Vision Models
• Humans and AI: Explainable AI (XAI) for Human Understanding
• Machine Learning: Large Multimodal Models (LMMs)

Application Category

• Search and Retrieval-Augmented AI: Retrieval-Augmented Generation (RAG) and multi-modal RAG
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• Web Mining and Content Analysis: Large pretrained models with web data

Abstract

The rapid advancement of Artificial Intelligence Generated Content (AIGC) in visual domains has resulted in highly realistic synthetic images and videos, driven by sophisticated generative frameworks such as diffusion-based architectures. While these breakthroughs open substantial opportunities, they simultaneously raise critical concerns about content authenticity and integrity. Many current AIGC detection methods operate as black-box binary classifiers, which offer limited interpretability, and no approach supports detecting both images and videos in a unified framework. This dual limitation compromises model transparency, reduces trustworthiness, and hinders practical deployment. To address these challenges, we introduce IVY-FAKE , a novel, unified, and large-scale dataset specifically designed for explainable multimodal AIGC detection. Unlike prior benchmarks, which suffer from fragmented modality coverage and sparse annotations, IVY-FAKE contains over 150,000 richly annotated training samples (images and videos) and 18,700 evaluation examples, each accompanied by detailed natural-language reasoning beyond simple binary labels. Building on this, we propose Ivy Explainable Detector (IVY-XDETECTOR), a unified AIGC detection and explainable architecture that jointly performs explainable detection for both image and video content. Our unified vision-language model achieves state-of-the-art performance across multiple image and video detection benchmarks, highlighting the significant advancements enabled by our dataset and modeling framework. Our data is publicly available at https://huggingface.co/datasets/AI-Safeguard/Ivy-Fake.

Problem

• Detects synthetic images and videos in unified framework
• Addresses lack of interpretability in AIGC detection methods
• Provides large-scale annotated dataset for explainable multimodal detection

Innovation

• Unified framework for image and video detection
• Explainable vision-language model architecture
• Large-scale dataset with rich annotations