通过挖掘生成模型的隐式噪声印记，提升对新生成图像的检测能力。
Revealing the Implicit Noise-based Imprint of Generative Models
- 构建噪声印记模拟器，捕捉不同生成模型的内在特征
- 在7个基准上实现顶尖检测性能，泛化性显著提升
- 适合关注AI图像安全与检测鲁棒性的研究者
随着视觉生成模型的快速发展，合成视觉内容带来的潜在安全风险日益受到关注，给AI生成图像检测带来重大挑战。现有方法普遍存在泛化能力不足的问题，在新兴生成模型上表现不佳。为此，本文提出NIRNet（基于噪声印记的揭示网络），利用噪声印记进行检测任务。我们设计了一种新型噪声印记模拟器，以捕捉不同生成模型在图像中留下的内在模式；通过聚合多种模型的印记，可外推未来模型的印记，扩充训练数据，增强泛化与鲁棒性。此外，我们提出新流程，首次将噪声印记提取器生成的噪声模式与其他视觉特征联合使用，显著提升检测性能。该方法在七个多样化基准上达到领先水平，包括五个公开数据集和两个新提出的泛化测试，充分证明其优越的泛化能力与有效性。
原文摘要 · Abstract (English)
With the rapid advancement of vision generation models, the potential security risks stemming from synthetic visual content have garnered increasing attention, posing significant challenges for AI-generated image detection. Existing methods suffer from inadequate generalization capabilities, resulting in unsatisfactory performance on emerging generative models. To address this issue, this paper presents NIRNet (Noise-based Imprint Revealing Network), a novel framework that leverages noise-based imprint for the detection task. Specifically, we propose a novel Noise-based Imprint Simulator to capture intrinsic patterns imprinted in images generated by different models. By aggregating imprint from various generative models, imprint of future models can be extrapolated to expand training data, thereby enhancing generalization and robustness. Furthermore, we design a new pipeline that pioneers the use of noise patterns, derived from a Noise-based Imprint Extractor, alongside other visual features for AI-generated image detection, significantly improving detection performance. Our approach achieves state-of-the-art performance across seven diverse benchmarks, including five public datasets and two newly proposed generalization tests, demonstrating its superior generalization and effectiveness. Paper Submission: pdf
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。