Detecting Diffusion-generated Images via Dynamic Assembly ForestsDetecting Diffusion-generated Images via Dynamic Assembly Forests

arXiv cs.CV / 4/13/2026

💬 OpinionIdeas & Deep AnalysisModels & Research

共有:

Key Points

拡散モデルが生成する画像の悪用リスクに対し、従来のCNN/Transformer等のDNN中心の検出アプローチとは別に、伝統的なMLでの検出可能性を検討しています。
深層フォレスト（deep forest）を土台にしたDynamic Assembly Forest（DAF）を提案し、特徴学習や大規模学習に関わるDNNの制約を補うことで、拡散生成画像検出を実現します。
DAFはDNNベース手法と比べてパラメータ数が少なく、計算コストも低く、GPUなしでのデプロイが可能である点が強調されています。
標準的な評価プロトコルで競争力のある性能を示したとされ、リソース制約のある環境での「重いDNNの実用的代替」になり得ると結論づけています。
コードとモデルがGitHubで公開されています（https://github.com/OUC-VAS/DAF）。

Abstract

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.