CalvinBackup/remove-ai-watermarks
1
0
Fork 0
mirror of https://github.com/wiltodelta/remove-ai-watermarks.git synced 2026-08-09 15:36:01 +02:00
Code Issues Packages Projects Releases Wiki Activity

Make the video SynthID operating point measurable and hard to move silently

Browse Source 
The shipped profile was certified by one oracle row, but only noise_std was
pinned: long_side and fps -- two thirds of what the verifier was actually shown
-- could move with a green suite. The test now derives the pin from
data/evaluations/video-synthid-oracle.csv, so a default without a certifying row
fails.

The certified profile is a perturbation-to-signal ratio, not a bare noise_std.
sd-vae-ft-mse publishes no scaling_factor key, so 0.18215 comes from the
AutoencoderKL class default under an upper-unbounded diffusers pin. The loader
now gates that value, carries it on VideoVaeRuntime, and passes it into encode
and decode so the validated value is the applied value. video_synthid_sweep.py
loads through the same function: the harness producing the certified rows was
the one path exempt from the gate it exists to feed.

psnr_db is measured against the already-resized frame and before the encoder, so
it cannot see the downscale, the decimation, or the codec, and no in-loop metric
can. scripts/video_fidelity_probe.py scores the delivered file end to end,
streaming the way the engine does and sharing its frame-selection rule rather
than copying it -- a frame-count check cannot catch a rule that reorders frames
without changing how many.

The manifest gains source geometry, vae, track, verbatim verdict and session
fields. The two 2026-07-31 rows keep them empty: they were never recorded and
are not recoverable. Verdicts now have four states, because the verifier's
unclear reading logged as not_detected is the silent regression the manifest
exists to prevent.

docs/video-synthid-quality-research.md records the research behind this: the
noise axis is worth about 2 dB and is nearly exhausted, resolution is the real
prize but is an uncertified destruction axis rather than a free win, and every
proposed autoencoder swap was refuted. First local measurements included.

Verified: engine output is byte-identical before and after the refactor on a
locally built clip, at noise_std 0.00 and 0.15.

Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
This commit is contained in:
Victor Kuznetsov
2026-08-05 11:17:38 -07:00
co-authored by Claude Opus 5
parent f481e6f944
commit 8fe0b0110f
14 changed files with 927 additions and 27 deletions
Download Patch File Download Diff File Expand all files Collapse all files
docs/synthid.md
+5
View File
@@ -372,6 +372,11 @@ itself. `0.15` is therefore the shipped default. The tracked manifest
`data/evaluations/video-synthid-oracle.csv` records the public source URL,
hashes, fidelity metrics, and verdicts without committing generated videos.
What that calibration does and does not constrain, the ranked experiment program
for trading less quality for the same removal, and the change candidates that were
refuted along the way are recorded in
[`video-synthid-quality-research.md`](video-synthid-quality-research.md).
The VAE perturbation follows the general regeneration-attack construction from
Zhao et al. The video-specific control and temporal metric are local additions.
VideoMarkBench motivates testing frame aggregation and matched perturbations,