الملخص
The proliferation of photorealistic AI-generated images demands robust detection methods that generalize across diverse generative models. While existing approaches target manipulation-based forgeries with local artifacts, generation-based images (e.g., from diffusion models) lack such traces, posing a fundamental challenge. We observe that generative models prioritize global semantics at the expense of local texture fidelity, making low-texture regions key indicators of synthetic origin. To exploit this, we propose EIB-Net, an Entropy-guided Information Bottleneck Network. EIB-Net introduces a novel Image Entropy (IE) metric to automatically select the most informative (lowest-entropy) patch, then processes it with a Variational Information Bottleneck (VIB) to learn compact, generalizable features. Extensive experiments on DIFF, DiffusionForensics, and GenImage benchmarks demonstrate state-of-the-art performance: EIB-Net achieves 85.7\% accuracy using only 2\% of training data, outperforming full-image baselines by over 15\%, and maintains robust cross-generator generalization (83.5\% average accuracy on GenImage). Furthermore, our entropy-guided patch selection (EGPL) consistently enhances diverse backbones (CNNs and Transformers), proving its practical value for data-efficient detection.
الكلمات المفتاحية
الموضوع
بيانات النشر
- المجلة
- غير متاح
- وصول مفتوح
- وصول مفتوح أخضر
اقتبس هذه المقالة
APA 7
Zhang, Z., Ma, X., & Cao, J. (2026). EIB-Net: Entropy-Guided Information Bottleneck for Generalizable AI-Generated Image Detection. https://omanscience.com/ar/articles/eib-net-entropy-guided-information-bottleneck-for-generalizable-ai-generated-image-detection
MLA 9
Zhang, Zhida, et al. "EIB-Net: Entropy-Guided Information Bottleneck for Generalizable AI-Generated Image Detection." https://omanscience.com/ar/articles/eib-net-entropy-guided-information-bottleneck-for-generalizable-ai-generated-image-detection.
شيكاغو (المؤلف–التاريخ)
Zhang, Zhida, Xinlei Ma, and Jie Cao. 2026. "EIB-Net: Entropy-Guided Information Bottleneck for Generalizable AI-Generated Image Detection." https://omanscience.com/ar/articles/eib-net-entropy-guided-information-bottleneck-for-generalizable-ai-generated-image-detection.
هارفارد
Zhang, Z., Ma, X. and Cao, J. (2026) 'EIB-Net: Entropy-Guided Information Bottleneck for Generalizable AI-Generated Image Detection', Available at: https://omanscience.com/ar/articles/eib-net-entropy-guided-information-bottleneck-for-generalizable-ai-generated-image-detection.
فانكوفر
Zhang Z, Ma X, Cao J. EIB-Net: Entropy-Guided Information Bottleneck for Generalizable AI-Generated Image Detection. https://omanscience.com/ar/articles/eib-net-entropy-guided-information-bottleneck-for-generalizable-ai-generated-image-detection
IEEE
Z. Zhang, X. Ma, and J. Cao, "EIB-Net: Entropy-Guided Information Bottleneck for Generalizable AI-Generated Image Detection," https://omanscience.com/ar/articles/eib-net-entropy-guided-information-bottleneck-for-generalizable-ai-generated-image-detection.