Skip to content

Live-web false positives on CDN-processed professional photography (smoke 2026-08-16) #32

Description

@felirami

Our pre-claim live smoke test of v1.2.0 FAILED: 266 of 1,093 images on assumed-real pages were flagged AI (24.3 percent), concentrated on professional photography served through image CDNs (Unsplash worst, Wikipedia completely clean at 0 of 264). Full findings, isolation experiments, and the fix plan: docs/live-smoke-2026-08-16.md.

Three causes identified so far:

  1. DINO probe saturation on current-era commercial photography (trained hard negatives were circa-2020 stock)
  2. CommunityForensics spiking on CDN-processed photos with large low-texture fields (real drone shot of water at CF 0.84)
  3. Part of the flagged set may be genuinely AI: Unsplash hosts labeled AI content in its 2026 feed, so the 24.3 percent needs ground-truthing before it is treated as the true false-positive rate

Work in progress: ground-truthed live corpus via Unsplash's public labels, probe retrain with current-distribution hard negatives, a permanent live-stress guard in the eval gate, and a full re-smoke. No bounty claim until the re-smoke passes.

How to help:

  • Reproduce any number with the Node harness (npm ci, npm run fetch-model, npm run eval -- ); it computes byte-identical model inputs to the extension
  • Post live counterexamples here: pages where real photos flag or AI images pass, ideally with exact image URLs
  • Recipes for labeled, redistributable live-CDN real-photo corpora directly improve the guard sets

Activity

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Metadata

Metadata

Assignees

No one assigned

    Labels

    No labels
    No labels

    Type

    No type

    Projects

    No projects

      Milestone

      No milestone

      Relationships

      None yet

      Development

      No branches or pull requests

      Issue actions