On the Exploitation of DCT-Traces in the Generative-AI Domain

Since their appearance, Deepfakes represent one of the toughest challenges in the world of Cybersecurity and Digital Forensics. In recent years, researchers have discovered that generative models leave unique traces in synthetic data that, if analyzed and identified in detail, can be exploited to improve the generalization limitations of existing deepfake detectors. To capture this evidence, in this paper we analyzed deepfake images in the frequency domain, examining in detail the beta-AC coefficients of the Discrete Cosine Transform (DCT). Recognizing …

challenges cs.cv cybersecurity data deepfake deepfakes digital domain exploitation forensics generative generative-ai generative models limitations researchers synthetic synthetic data traces world