A robust synthetic face detector in OSN context based on Gradient of Color features

Extensive development in Generative Artificial Intelligence and the growth of Online Social Networks have facilitated the creation and sharing of synthetic images like never before. This has led to an overwhelming increase in the dissemination of fake content on OSNs. Maintaining the integrity of OSNs is paramount, and detecting synthetic images plays a crucial role in preserving social balance. Existing solutions, while achieving perfect detection performance on test datasets, often experience significant degradation when applied to OSN images. In our work, we propose a robust fake image detector that relies on features minimally affected by common OSN perturbations. Specifically, our solution leverages gradient features in color channels, including chrominance and luminance channels, accompanied by a residual-based CNN. Our low-parameterized solution is characterized by low complexity, making it particularly resource-efficient and suitable for edge devices. Thorough experiments demonstrate that our method achieves 100% accuracy in identifying fake images on our test dataset. We further evaluate the approach on images generated by contemporary generative adversarial networks and diffusion models, where it consistently exhibits strong detection performance. In addition, when applied to images that undergo post-processing operations designed to mimic OSN circulation, the proposed detector maintains high accuracy and robustness. Overall, results indicate that our proposed gradient-based color-channel features, coupled with a low-complexity residual network, provide an effective and OSN-resilient solution for synthetic image detection across both generic and post-processed/compressed scenarios.