AI RESEARCH
Combating Pattern and Content Bias: Adversarial Feature Learning for Generalized AI-Generated Image Detection
arXiv CS.CV
•
ArXi:2604.12353v1 Announce Type: new In recent years, the rapid development of generative artificial intelligence technology has significantly lowered the barrier to creating high-quality fake images, posing a serious challenge to information authenticity and credibility. Existing generated image detection methods typically enhance generalization through model architecture or network design. However, their generalization performance remains susceptible to data bias, as the