用轻量级森林模型检测扩散生成图像，无需GPU也能高效运行。
Detecting Diffusion-generated Images via Dynamic Assembly Forests
- 基于深度森林架构设计动态组装森林，提升特征学习能力。
- 参数量少、计算成本低，在标准测试中表现媲美深度神经网络。
- 适合资源受限场景，如移动端或边缘设备部署。
扩散模型能生成高质量图像，带来严重安全风险。现有方法多依赖深度神经网络（如CNN和Transformer），却忽视了传统机器学习模型的潜力。本文首次探索此类替代方案，提出一种新型动态组装森林模型（DAF）用于检测扩散生成图像。该模型基于深度森林范式，解决了特征学习不足与可扩展训练的固有缺陷，成为高效的扩散图像检测器。相比现有基于DNN的方法，DAF参数更少、计算开销更低，且无需GPU即可部署，同时在标准评估协议下表现竞争力。结果表明，该方法在资源受限场景中可作为重型DNN模型的实用替代方案。代码与模型已公开于https://github.com/OUC-VAS/DAF。
原文摘要 · Abstract (English)
Diffusion models are known for generating high-quality images, causing serious security concerns. To combat this, most efforts rely on deep neural networks (e.g., CNNs and Transformers), while largely overlooking the potential of traditional machine learning models. In this paper, we freshly investigate such alternatives and proposes a novel Dynamic Assembly Forest model (DAF) to detect diffusion-generated images. Built upon the deep forest paradigm, DAF addresses the inherent limitations in feature learning and scalable training, making it an effective diffusion-generated image detector. Compared to existing DNN-based methods, DAF has significantly fewer parameters, much lower computational cost, and can be deployed without GPUs, while achieving competitive performance under standard evaluation protocols. These results highlight the strong potential of the proposed method as a practical substitute for heavyweight DNN models in resource-constrained scenarios. Our code and models are available at https://github.com/OUC-VAS/DAF.
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。