FerretNet: Efficient Synthetic Image Detection via Local Pixel Dependencies

The increasing realism of synthetic images generated by advanced models such as VAEs, GANs, and LDMs poses significant challenges for synthetic image detection. To address this issue, we explore two artifact types introduced during the generation process: (1) latent distribution deviations and (2) decoding-induced smoothing effects, which manifest as inconsistencies in local textures, edges, and color transitions. Leveraging local pixel dependencies (LPD) properties rooted in Markov Random Fields, we reconstruct synthetic images using neighboring pixel information to expose disruptions in texture continuity and edge coherence. Building upon LPD, we propose FerretNet, a lightweight neural network with only 1.1M parameters that delivers efficient and robust synthetic image detection. Extensive experiments demonstrate that FerretNet, trained exclusively on the 4-class ProGAN dataset, achieves an average accuracy of 97.1% on an open-world benchmark comprising 22 generative models. Our code and datasets are publicly available at https://github.com/xigua7105/FerretNet.

Key Contributions

• Novel Local Pixel Dependencies (LPD) representation using Markov Random Fields and median-based reconstruction to expose generation artifacts (latent distribution deviations and decoding-induced smoothing) across GAN, VAE, and LDM architectures
• FerretNet: a lightweight 1.1M-parameter detector using depthwise separable and dilated convolutions that achieves 97.1% accuracy on 22 generative models when trained only on a 4-class ProGAN dataset
• Synthetic-Pop: a new 60K-image open-world benchmark covering six high-fidelity generators for evaluating synthetic image detectors

🛡️ Threat Analysis

Details

Similar Papers