mirror of
https://github.com/wiltodelta/remove-ai-watermarks.git
synced 2026-08-27 16:02:28 +02:00
Victor KuznetsovandClaude Fable 4.5
e09104e39f
Muse Image (muse-image-1.0, Meta Superintelligence Labs, 2026-07-07) ships every output with Content Seal, a proprietary invisible pixel watermark, and no visible mark. Establish support documentation and a verified corpus: - data/contentseal/: five own generations via the Meta Model API, every oracle verdict recorded in manifest.csv (44 rows, settled-text protocol, fresh-navigation variant for calibration rows) - Oracle: meta.ai/identification web tool only; no API endpoint exists in the Meta Model API (verified against dev.meta.ai/docs); internal REST pair documented with its server-side sliding-window rate limit - Removal: default qwen-zimage profile clears Content Seal (oracle-verified on the worst source); strength floor derived at 0.1 by the standard worst-boundary-plus-cross-source-spread method, recorded but not encoded as a constant since no provenance signal routes Muse output onto a vendor cohort - Seal robustness measured: survives resize, JPEG q85, metadata stripping, CDN WebP transcode; dies to center crops and diffusion regeneration - tests/test_contentseal_corpus.py guards manifest integrity Co-Authored-By: Claude Fable 4.5 <noreply@anthropic.com>
61 lines
2.3 KiB
Python
61 lines
2.3 KiB
Python
"""Tests for the Content Seal oracle corpus layout.
|
|
|
|
Mirrors the synthid corpus guard: the manifest is the source of truth for
|
|
which binaries exist, and every recorded hash must match the file it names.
|
|
Derived rows are recipes, not stored files, so only originals are checked
|
|
against disk.
|
|
"""
|
|
|
|
from __future__ import annotations
|
|
|
|
import csv
|
|
import hashlib
|
|
import re
|
|
from pathlib import Path
|
|
|
|
CORPUS_DIR = Path(__file__).resolve().parent.parent / "data" / "contentseal"
|
|
MANIFEST = CORPUS_DIR / "manifest.csv"
|
|
ORIGINALS = CORPUS_DIR / "originals"
|
|
|
|
_SHA256 = re.compile(r"^[0-9a-f]{64}$")
|
|
_VALID_VERDICTS = {"detected", "not_detected", ""}
|
|
_VALID_ORIGINS = {"meta-model-api", "derived", "meta-blog-cdn", "synthetic-local"}
|
|
|
|
|
|
def _manifest_rows() -> list[dict[str, str]]:
|
|
with open(MANIFEST, newline="") as f:
|
|
return list(csv.DictReader(f))
|
|
|
|
|
|
def test_manifest_original_rows_match_binaries_and_hashes() -> None:
|
|
rows = [r for r in _manifest_rows() if r["file"]]
|
|
stored = {path.name for path in ORIGINALS.iterdir() if path.is_file()}
|
|
assert {r["file"].removeprefix("originals/") for r in rows} == stored
|
|
|
|
for row in rows:
|
|
digest = hashlib.sha256((CORPUS_DIR / row["file"]).read_bytes()).hexdigest()
|
|
assert digest == row["sha256"], row["file"]
|
|
|
|
|
|
def test_manifest_rows_are_well_formed() -> None:
|
|
rows = _manifest_rows()
|
|
assert len({row["sha256"] for row in rows}) == len(rows), "duplicate sha256"
|
|
|
|
for row in rows:
|
|
assert _SHA256.match(row["sha256"]), row["name"]
|
|
assert row["origin"].split(":")[0] in _VALID_ORIGINS, row["name"]
|
|
assert row["oracle_verdict"] in _VALID_VERDICTS, row["name"]
|
|
# Every oracle verdict must carry its check timestamp.
|
|
if row["oracle_verdict"]:
|
|
assert row["checked_at_utc"], row["name"]
|
|
# Detection rows must name the oracle attribution.
|
|
if row["oracle_verdict"] == "detected":
|
|
assert "Muse Image 1" in row["oracle_attribution"], row["name"]
|
|
|
|
|
|
def test_default_pipeline_clearance_is_recorded() -> None:
|
|
"""The verified claim that the default profile clears Content Seal must stay."""
|
|
rows = {row["name"]: row for row in _manifest_rows()}
|
|
for name in ("fox_modal_invisible", "text_modal_invisible"):
|
|
assert rows[name]["oracle_verdict"] == "not_detected", name
|