EIB-Net: Entropy-Guided Information Bottleneck for Generalizable AI-Generated Image Detection

EIB-Net is an Entropy‑Guided Information Bottleneck Network designed to detect AI‑generated images across diverse generative models. It introduces an Image Entropy metric to automatically select the most informative, low‑entropy patch and applies a Variational Information Bottleneck to learn compact, generalizable features. Experiments on DIFF, DiffusionForensics, and GenImage benchmarks show state‑of‑the‑art performance, achieving 85.7% accuracy with only 2% of training data and maintaining robust cross‑generator generalization.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv AI.

• llms
• diffusion
• robotics
• benchmarks