将AI生成图像溯源转化为检索问题，实现无需模型即可精准识别来源。
Attribution as Retrieval: Model-Agnostic AI-Generated Image Attribution
- 把溯源任务当作图像检索，不依赖具体生成模型。
- 零样本和少样本下均达顶尖性能，检测准确率超现有方法。
- 适合需要快速应对新生成模型的图像安全场景。
随着AIGC技术的快速发展，图像取证面临前所未有的挑战。传统方法难以应对不断演进的生成技术所产生的高度逼真图像。为促进AI生成图像的识别与来源追溯，生成式图像水印和AI生成图像溯源成为近年研究重点。然而，现有方法多依赖特定生成模型，需访问源模型，缺乏通用性与可扩展性。为此，本文提出一种新范式：将溯源问题转化为实例检索任务。我们设计了高效的模型无关框架LIDA（Low-bIt-plane-based Deepfake Attribution）。输入由低比特指纹生成模块产生，训练过程包含无监督预训练与后续少量样本适配。大量实验表明，LIDA在零样本和少样本设置下，对深度伪造检测与图像溯源均达到当前最优表现。代码已开源。
原文摘要 · Abstract (English)
With the rapid advancement of AIGC technologies, image forensics will encounter unprecedented challenges. Traditional methods are incapable of dealing with increasingly realistic images generated by rapidly evolving image generation techniques. To facilitate the identification of AI-generated images and the attribution of their source models, generative image watermarking and AI-generated image attribution have emerged as key research focuses in recent years. However, existing methods are model-dependent, requiring access to the generative models and lacking generality and scalability to new and unseen generators. To address these limitations, this work presents a new paradigm for AI-generated image attribution by formulating it as an instance retrieval problem instead of a conventional image classification problem. We propose an efficient model-agnostic framework, called Low-bIt-plane-based Deepfake Attribution (LIDA). The input to LIDA is produced by Low-Bit Fingerprint Generation module, while the training involves Unsupervised Pre-Training followed by subsequent Few-Shot Attribution Adaptation. Comprehensive experiments demonstrate that LIDA achieves state-of-the-art performance for both Deepfake detection and image attribution under zero- and few-shot settings. The code is at https://github.com/hongsong-wang/LIDA
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。