Distinguere tra immagini reali e generate dall’intelligenza artificiale, commonly referred to as
‘image detection’, rappresenta una sfida attuale e significativa. Nonostante
extensive research in the (semi-)regime vigilato, zero-shot and few-shot
solutions have only recently emerged as promising alternatives. Their main
advantage is in alleviating the ongoing data maintenance, which quickly becomes
outdated due to advances in generative technologies. We identify two main gaps:
(1) a lack of theoretical grounding for the methods, E (2) significant room
for performance improvements in zero-shot and few-shot regimes. Our approach is
founded on understanding and quantifying the biases inherent in generated
content, where we use these quantities as criteria for characterizing generated
images. Nello specifico, we explore the biases of the implicit probability
manifold, captured by a pre-trained diffusion model. Through score-function
analysis, we approximate the curvature, gradient, and bias towards points on
the probability manifold, establishing criteria for detection in the zero-shot
regime. We further extend our contribution to the few-shot setting by employing
a mixture-of-experts methodology. Empirical results across 20 generative models
demonstrate that our method outperforms current approaches in both zero-shot
and few-shot settings. This work advances the theoretical understanding and
practical usage of generated content biases through the lens of manifold
analysis.

Questo articolo esplora i giri e le loro implicazioni.

Scarica PDF: