|国家预印本平台
首页|MLEP: Multi-granularity Local Entropy Patterns for Universal AI-generated Image Detection

MLEP: Multi-granularity Local Entropy Patterns for Universal AI-generated Image Detection

MLEP: Multi-granularity Local Entropy Patterns for Universal AI-generated Image Detection

来源:Arxiv_logoArxiv
英文摘要

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.

Lin Yuan、Xiaowan Li、Yan Zhang、Jiawei Zhang、Hongbo Li、Xinbo Gao

计算技术、计算机技术

Lin Yuan,Xiaowan Li,Yan Zhang,Jiawei Zhang,Hongbo Li,Xinbo Gao.MLEP: Multi-granularity Local Entropy Patterns for Universal AI-generated Image Detection[EB/OL].(2025-04-18)[2025-04-27].https://arxiv.org/abs/2504.13726.点此复制

评论