Diffusion-based generators have made synthetic images ubiquitous, but detectors often fail under simultaneous shifts in generator, prompt/style, and source-domain. We study AI-generated image detection as a transfer system described by training prior, frozen encoder feature space, and decision rule, and ask when classifier head training adds value beyond what is already separable in modern features. As a controlled diagnostic, we fit a prior-conditioned Gaussian discriminant ladder: closed-form heads built from first- and second-order feature statistics under nested covariance assumptions. On Percept-Lens, a unified protocol over 39 public datasets (7.1 million images), the best rung is frequently competitive with, and sometimes exceeds, released AI-generated image detector heads when matched on both prior and encoder. We further quantify strong sensitivity to the training prior, data-efficiency of moment-based heads, and representation dependence of Gaussian shift metrics, motivating (prior, encoder, head)-level reporting and stronger analytical baselines for AIGI transfer.
Figures & tables
Figure 1: Training-prior-conditioned Gaussian discriminants in a frozen feature space. A frozen image encoder ϕ maps images x to embeddings z . Given a (possibly few-shot) support set S drawn from a training prior , we estimate class-conditional moments (μc,Σc) and instantiate a ladder of classical closed-form heads under nested covariance assumptions. By keeping the encoder and prior fixed, the ladder isolates what the decision rule contributes.
Figure 2: Gaussian discriminant ladder as nested covariance assumptions. Each rung is a classical generative classifier obtained by restricting the class-conditional covariance: isotropic (Euc-/Cos-NCM), diagonal (GNB), shared full covariance (Mah-NCM), or class-specific full covariance (QDA). This nested family makes it possible to diagnose how much transferable signal is captured by first- and second-order feature statistics.
Assumes spherical class distributions; decision is based on angular proximity, suitable for normalized embeddings.
Gaussian Naive Bayes (GNB)
Diagonal
Σc∈{0,1}=diag(σc,j2)
Non-Linear
Simplest model; assumes feature independence, useful for identifying decorrelated representations.
Mahalanobis Nearest Centroid Matching (Mah-NCM)
Homoscedastic
Σ0=Σ1=Σp
Linear
Assumes classes share the same elliptical shape. It accounts for feature correlations by whitening the space, yielding a correlation-aware linear boundary.
Quadratic Discriminant Analysis (QDA)
Heteroscedastic
Σ0=Σ1
Quadratic
Most general model; allows each class to have a unique elliptical shape and orientation, capturing complex separations.
Table 1: Gaussian discriminant ladder used as analytical baselines. Each rung is a generative classifier obtained by restricting the class-conditional covariance (isotropic, diagonal, homoscedastic, or heteroscedastic), which determines the geometry of the induced decision boundary. We use this ladder to isolate head effects in a fixed frozen encoder feature space rather than to propose a new detector.
Figure 3: Percept-Lens stress-tests detectors under joint distribution shift. Percept-Lens is an evaluation protocol built entirely from existing public datasets. Many AIGI evaluations vary either the generator family or the image source in isolation; we instead evaluate under joint shifts in generator family, prompt/style, and source domain, closer to deployment where these factors drift together.
Table 2: Closed-form Gaussian discriminants versus released AI-generated image detector heads under matched (prior, encoder) conditions. Mean class accuracy CA (dataset-wise balanced accuracy where defined; Section 5.1 ), macro-averaged across Percept-Lens evaluation datasets. For each released detector checkpoint, we report (i) the released decision head ( Out-of-the-Shelf ) and (ii) closed-form baselines fitted on the same frozen encoder features using the corresponding public training prior: Euc-NCM ( Wu et al., 2025b ) and the best-performing rung of the Gaussian ladder. The full ladder is reported in Section 5.2 . (Parentheses indicate the training subset reported by the original work when applicable.)
AI-generated image detection identifies synthetic or AI-edited images and develops methods that generalize across generators, domains, and image transformations.