用多尺度像素熵模式检测AI生成图像，提升跨模型泛化能力。
MLEP: Multi-granularity Local Entropy Patterns for Universal AI-generated Image Detection
- 通过打乱小块图像并计算多尺度熵图，捕捉像素间关系。
- 在32种生成模型上测试，准确率和泛化性均超越现有方法。
- 适合需要跨模型检测的AI图像安全场景使用。
图像生成技术的进步引发了虚假信息和深度伪造等滥用担忧，亟需有效检测AI生成图像（AIGI）的方法。尽管已有进展，但现有方法因缺乏源无关特征且泛化能力有限，难以在不同生成模型和场景下保持可靠性能。本文探索以图像熵为线索，提出多粒度局部熵模式（MLEP），通过在多尺度下对打乱的小块图像计算熵特征图，全面捕捉跨维度与尺度的像素关系，同时显著破坏图像语义，减少内容偏差。基于MLEP训练的稳健卷积神经网络分类器可实现高效AIGI检测。在开放世界场景下，针对32种不同生成模型合成的图像进行的广泛实验表明，该方法在准确率和泛化能力上均显著优于当前最优方法。
原文摘要 · Abstract (English)
Advancements in image generation technologies have raised significant concerns about their potential misuse, such as producing misinformation and deepfakes. Therefore, there is an urgent need for effective methods to detect AI-generated images (AIGI). Despite progress in AIGI detection, achieving reliable performance across diverse generation models and scenes remains challenging due to the lack of source-invariant features and limited generalization capabilities in existing methods. In this work, we explore the potential of using image entropy as a cue for AIGI detection and propose Multi-granularity Local Entropy Patterns (MLEP), a set of entropy feature maps computed across shuffled small patches over multiple image scaled. MLEP comprehensively captures pixel relationships across dimensions and scales while significantly disrupting image semantics, reducing potential content bias. Leveraging MLEP, a robust CNN-based classifier for AIGI detection can be trained. Extensive experiments conducted in an open-world scenario, evaluating images synthesized by 32 distinct generative models, demonstrate significant improvements over state-of-the-art methods in both accuracy and generalization.
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。