DriftScope: Measuring The Hidden Effects of Diffusion Model Adaptation
arXiv cs.CV1mo4 min read
arXiv:2607.00183v1 Announce Type: new Abstract: Adapting pre-trained text-to-image diffusion models, whether to learn new visual concepts or erase unwanted ones, is routinely evaluated on its intended effects alone. We argue this framing is incomplete. Through sparse autoencoder analysis and zero-shot classification, we demonstrate that adaptation systematically damages semantically unrelated concepts in ways that aggregate metrics structurally cannot surface: when damage is severe enough for FID and KID to respond, the model is already nearly unusable; when the model remains functional, FID a
