系统梳理生成图像检测方法与挑战，助力识别深度伪造内容。
Fully AI-Generated Image Detection: Definition, Recent Advances and Challenges
- 按数据集构建与特征提取两阶段分析检测框架
- 强调数据设计对模型泛化能力的关键影响
- 适合关注AI安全与媒体鉴伪的研究者阅读
视觉生成模型的最新进展已能无需真实源内容即可生成高度逼真的全量AI生成图像。尽管这对诸多应用有益，但也带来显著社会风险，易被滥用制造令人信服的深度伪造。检测此类图像构成人工智能媒体鉴伪中的基础且具挑战性问题，要求检测器可靠提取生成架构固有的痕迹特征。本文综述了全量AI生成图像检测的系统性进展。遵循标准检测器设计流程，聚焦数据集构建与特征提取两大核心环节。分析数据集设计如何影响所学特征的泛化性与鲁棒性，并根据提取方法依赖的主要归纳偏置进行分类。在此框架下，系统回顾现有工作。最后，指出开放问题并展望未来发展方向。本综述涵盖的工作可于 https://github.com/zju-pi/Awesome-Fully-AI-Generated-Image-Detection 获取。
原文摘要 · Abstract (English)
Recent advances in visual generative models have enabled the creation of highly realistic, fully AI-generated images without relying on real source content. While beneficial for many applications, these models also pose significant societal risks, as they can be easily exploited to produce convincing Deepfakes. Detecting them represents a foundational yet challenging problem in AI media forensics, requiring detectors to reliably extract the inherent artifacts imprinted by generative architectures. In this Review, we provide a systematic overview of fully AI-generated image detection. Following the standard detector design pipeline, we focus on two key components: dataset construction and artifact extraction. We analyze how dataset design influences the generalization and robustness of learned artifacts, and categorize existing artifact extraction methods based on the primary inductive priors leveraged to isolate artifacts. Within this framework, we systematically review existing works. Finally, we highlight open problems and envision several future directions for developing more robust and generalizable detectors. Reviewed works in this survey can be found at https://github.com/zju-pi/Awesome-Fully-AI-Generated-Image-Detection.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。