feat: detect soft-binding vendors, IPTC 2025.1, video/audio C2PA, TrustMark (v0.6.0)

Broadens metadata provenance coverage at the detection and container-strip level.

Detection:
- C2PA soft-binding `alg` -> forensic-watermark vendor (Adobe TrustMark,
  Digimarc, Imatag, Steg.AI, Microsoft, ...) via C2PA_SOFT_BINDINGS +
  soft_binding_vendors_in(); names the watermark vendor even when the watermark
  itself can't be decoded.
- IPTC Photo Metadata 2025.1 AI-disclosure XMP fields (AISystemUsed etc.) via
  iptc_ai_system() + IPTC_AI_FIELD_MARKERS.
- Adobe TrustMark open keyless decoder (trustmark_detector.py, optional extra
  `trustmark`) -- the watermark behind Adobe Durable Content Credentials.
  Detects provenance, not AI origin, so it does not assert is_ai.

Removal / containers:
- isobmff.strip_c2pa_boxes now also drops a top-level XMP uuid box that carries
  an AI label (matched by AI-marker content, byte-order-robust; plain XMP kept).
- remove_ai_metadata routes MP4/MOV/M4V/M4A (and any ftyp-sniffed ISOBMFF)
  through the box stripper; raises a clear error for non-ISOBMFF audio/video
  (WebM/MP3/WAV) instead of crashing in the image path.

Tests: soft-binding scan, IPTC element/attribute/presence, MP4 + M4A detect/
strip, ISOBMFF XMP surgical strip, content-sniff, unsupported-container guard,
TrustMark absent-safety + identify integration. ruff clean; pyright clean on
all new modules.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

src/remove_ai_watermarks/__init__.py

@@ -1,3 +1,3 @@
 """Remove-AI-Watermarks: Unified tool for removing visible and invisible AI watermarks."""
 
-__version__ = "0.5.6"
+__version__ = "0.6.0"

src/remove_ai_watermarks/identify.py

@@ -26,13 +26,15 @@ from remove_ai_watermarks.metadata import (
     AI_METADATA_KEYS,
     AIGC_MARKERS,
     C2PA_UUID,
+    IPTC_AI_FIELD_MARKERS,
     IPTC_AI_MARKERS,
     aigc_label,
     exif_generator,
     get_ai_metadata,
+    iptc_ai_system,
     xai_signature,
 )
-from remove_ai_watermarks.noai.c2pa import extract_c2pa_info
+from remove_ai_watermarks.noai.c2pa import extract_c2pa_info, soft_binding_vendors_in
 from remove_ai_watermarks.noai.constants import C2PA_AI_TOOLS, C2PA_ISSUERS
 
 if TYPE_CHECKING:
@@ -162,6 +164,17 @@ def _invisible_watermark(image_path: Path) -> str | None:
     return detect_invisible_watermark(image_path)
 
 
+def _trustmark(image_path: Path) -> str | None:
+    """Adobe TrustMark scheme name or None.
+
+    Optional: needs the ``trustmark`` decoder (extra ``trustmark``). Returns None
+    if it is not installed or no TrustMark watermark decodes.
+    """
+    from remove_ai_watermarks.trustmark_detector import detect_trustmark
+
+    return detect_trustmark(image_path)
+
+
 def identify(image_path: Path, *, check_visible: bool = True, check_invisible: bool = True) -> ProvenanceReport:
     """Identify an image's origin platform and watermark inventory.
 
@@ -213,6 +226,14 @@ def identify(image_path: Path, *, check_visible: bool = True, check_invisible: b
         if "OpenAI" in (" ".join(issuers) + synthid):
             caveats.append(_OPENAI_CAVEAT)
 
+    # ── C2PA soft-binding: a named forensic/third-party watermark vendor ─
+    # (Adobe TrustMark, Digimarc, Imatag, ...). Present in the manifest even when
+    # the watermark itself can't be decoded; names whose watermark stamped the pixels.
+    soft_binding = meta.get("soft_binding") or (", ".join(v) if (v := soft_binding_vendors_in(head)) else None)
+    if soft_binding:
+        signals.append(Signal("soft_binding", f"C2PA soft binding: {soft_binding}", "high"))
+        watermarks.append(f"Forensic watermark soft binding ({soft_binding})")
+
     # ── IPTC "Made with AI" (Meta etc.), only meaningful without C2PA ─
     iptc = any(m in head for m in IPTC_AI_MARKERS)
     if iptc and not has_c2pa:
@@ -222,6 +243,18 @@ def identify(image_path: Path, *, check_visible: bool = True, check_invisible: b
         if platform is None:
             platform = "Made-with-AI tag (e.g. Meta AI); platform not specified"
 
+    # ── IPTC 2025.1 AI-disclosure fields (Iptc4xmpExt:AISystemUsed etc.) ─
+    iptc_ai = any(m in head for m in IPTC_AI_FIELD_MARKERS)
+    if iptc_ai:
+        system = iptc_ai_system(image_path)
+        named = bool(system) and system != "fields present"
+        signals.append(
+            Signal("iptc_ai_system", f"IPTC AI disclosure ({system})" if named else "IPTC AI disclosure fields", "high")
+        )
+        watermarks.append(f"IPTC 2025.1 AI disclosure ({system})" if named else "IPTC 2025.1 AI disclosure fields")
+        if platform is None and named:
+            platform = f"{system} (IPTC AISystemUsed)"
+
     # ── China TC260 AIGC label (Doubao and other China-served gens) ──
     aigc = any(m in head for m in AIGC_MARKERS)
     if aigc:
@@ -266,12 +299,29 @@ def identify(image_path: Path, *, check_visible: bool = True, check_invisible: b
         if platform is None:
             platform = f"{scheme} (open DWT-DCT watermark)"
 
+    # ── Adobe TrustMark invisible watermark (open decoder, no key) ───
+    # The watermark behind Adobe Durable Content Credentials. Decoded locally,
+    # but it binds provenance for human-authored content too, so it enriches the
+    # watermark inventory without by itself asserting AI origin.
+    if check_invisible and (tm_scheme := _trustmark(image_path)) is not None:
+        signals.append(Signal("trustmark", tm_scheme, "high"))
+        watermarks.append(f"Adobe TrustMark invisible watermark ({tm_scheme})")
+        if platform is None:
+            platform = "Adobe (TrustMark / Content Credentials)"
+
     # ── Verdict so far (metadata + embedded watermark) ──────────────
     invisible_wm = any(s.name == "invisible_watermark" for s in signals)
     exif_gen = any(s.name == "exif_generator" for s in signals)
     xai_sig = any(s.name == "xai_signature" for s in signals)
     ai_from_metadata = bool(
-        (has_c2pa and (c2pa_is_ai or synthid)) or iptc or aigc or local_keys or invisible_wm or exif_gen or xai_sig
+        (has_c2pa and (c2pa_is_ai or synthid))
+        or iptc
+        or iptc_ai
+        or aigc
+        or local_keys
+        or invisible_wm
+        or exif_gen
+        or xai_sig
     )
 
     # ── Visible Gemini sparkle (fallback for stripped-metadata case) ─

src/remove_ai_watermarks/metadata.py

@@ -74,6 +74,29 @@ IPTC_AI_MARKERS: tuple[bytes, ...] = (
     b"compositeWithTrainedAlgorithmicMedia",
 )
 
+# IPTC Photo Metadata 2025.1 (published 2025-11-27) added explicit AI-disclosure
+# XMP properties in the Iptc4xmpExt namespace. Their mere presence is an AI
+# signal; ``AISystemUsed`` additionally carries the generator name. Property
+# tokens verified against the IPTC 2025.1 specification.
+IPTC_AI_FIELD_MARKERS: tuple[bytes, ...] = (
+    b"AISystemUsed",
+    b"AISystemVersionUsed",
+    b"AIPromptInformation",
+    b"AIPromptWriterName",
+)
+
+# ISOBMFF containers whose AI-provenance boxes ``remove_ai_metadata`` strips at
+# the container level (image, video, audio -- all ISOBMFF). A content sniff
+# (``ftyp``) is also accepted, so this is a fast-path hint, not the sole gate.
+_ISOBMFF_EXTS: frozenset[str] = frozenset({".avif", ".heif", ".heic", ".jxl", ".mp4", ".mov", ".m4v", ".m4a"})
+
+# Non-ISOBMFF audio/video we can DETECT (binary scan) but not strip at the
+# container level (EBML / framed / RIFF need re-encoding). remove_ai_metadata
+# fails clearly on these rather than crashing in the image path.
+_UNSUPPORTED_CONTAINER_EXTS: frozenset[str] = frozenset(
+    {".webm", ".mkv", ".mka", ".mp3", ".wav", ".flac", ".ogg", ".oga", ".opus", ".aac"}
+)
+
 # China's mandatory AI-content labeling (TC260, the national cybersecurity
 # standards committee). AI generators serving China embed an XMP block in the
 # TC260 namespace -- ``<TC260:AIGC>{"Label":"1",...}``. Doubao (ByteDance) uses
@@ -155,6 +178,9 @@ def has_ai_metadata(image_path: Path) -> bool:
         return True
     if any(marker in data for marker in IPTC_AI_MARKERS):
         return True
+    # IPTC 2025.1 AI-disclosure XMP properties (their presence flags AI content).
+    if any(marker in data for marker in IPTC_AI_FIELD_MARKERS):
+        return True
     # xAI / Grok: no C2PA/IPTC/XMP -- only the EXIF Signature + UUID-Artist pair.
     return xai_signature(image_path)
 
@@ -183,6 +209,26 @@ def aigc_label(image_path: Path) -> dict[str, str] | None:
     return {str(k): str(v) for k, v in parsed.items()} if isinstance(parsed, dict) else None
 
 
+def iptc_ai_system(image_path: Path) -> str | None:
+    """Return an IPTC 2025.1 AI-disclosure note if the file carries those XMP
+    properties, else None.
+
+    IPTC Photo Metadata 2025.1 added ``Iptc4xmpExt`` AI-disclosure properties
+    (see ``IPTC_AI_FIELD_MARKERS``); their presence alone flags AI content, and
+    ``AISystemUsed`` names the generator. Returns the ``AISystemUsed`` value when
+    extractable, otherwise the literal ``"fields present"``. Container-agnostic
+    raw-byte scan; handles both XMP element and attribute serializations.
+    """
+    with open(image_path, "rb") as f:
+        data = f.read(1024 * 1024)
+    if not any(marker in data for marker in IPTC_AI_FIELD_MARKERS):
+        return None
+    match = re.search(rb"AISystemUsed[=:\s]*[\"'>]\s*([^<\"']{1,120})", data)
+    if match and (value := match.group(1).decode("utf-8", "replace").strip()):
+        return value
+    return "fields present"
+
+
 def synthid_source(image_path: Path) -> str | None:
     """Return the vendor name(s) if the image carries a SynthID pixel watermark.
 
@@ -380,7 +426,7 @@ def get_ai_metadata(image_path: Path) -> dict[str, str]:
     """
     from PIL import Image
 
-    from remove_ai_watermarks.noai.c2pa import extract_c2pa_info, synthid_verdict
+    from remove_ai_watermarks.noai.c2pa import extract_c2pa_info, soft_binding_vendors_in, synthid_verdict
 
     result: dict[str, str] = {}
 
@@ -410,14 +456,21 @@ def get_ai_metadata(image_path: Path) -> dict[str, str]:
         "source_type",
         "actions",
         "synthid_watermark",
+        "soft_binding",
     ):
         if key in c2pa:
             result.setdefault(key, str(c2pa[key]))
 
-    # Non-PNG containers (JPEG/WebP/AVIF): extract_c2pa_info is PNG-only, so
-    # fall back to the format-agnostic source check for the SynthID verdict.
+    # Non-PNG containers (JPEG/WebP/AVIF/MP4): extract_c2pa_info is PNG-only, so
+    # fall back to the format-agnostic source check for the SynthID verdict and
+    # the soft-binding (forensic-watermark vendor) scan.
     if "synthid_watermark" not in result and (vendor := synthid_source(image_path)):
         result.setdefault("synthid_watermark", synthid_verdict(vendor))
+    if "soft_binding" not in result:
+        with open(image_path, "rb") as f:
+            head = f.read(1024 * 1024)
+        if vendors := soft_binding_vendors_in(head):
+            result["soft_binding"] = ", ".join(vendors)
 
     # China TC260 AI-content label (Doubao and other China-served generators).
     if aigc := aigc_label(image_path):
@@ -427,6 +480,10 @@ def get_ai_metadata(image_path: Path) -> dict[str, str]:
     # xAI / Grok EXIF signature scheme (its only provenance signal).
     if xai_signature(image_path):
         result.setdefault("xai_signature", "xAI/Grok EXIF signature (Artist UUID + Signature blob)")
+
+    # IPTC 2025.1 AI-disclosure XMP fields (Iptc4xmpExt:AISystemUsed etc.).
+    if system := iptc_ai_system(image_path):
+        result.setdefault("ai_system", f"IPTC 2025.1 AI disclosure ({system})")
     return result
 
 
@@ -455,19 +512,34 @@ def remove_ai_metadata(
     if output_path is None:
         output_path = source_path
 
-    # AVIF/HEIF/JPEG-XL: strip C2PA boxes at the container level without
-    # re-encoding. Avoids needing PIL plugins (pillow-heif / pillow-jxl) and
-    # preserves pixel data bit-for-bit.
-    if source_path.suffix.lower() in (".avif", ".heif", ".heic", ".jxl"):
-        from remove_ai_watermarks.noai.isobmff import strip_c2pa_boxes
+    # ISOBMFF containers (AVIF/HEIF/JPEG-XL images, MP4/MOV/M4V video, M4A audio):
+    # strip C2PA + AI-label boxes at the container level without re-encoding.
+    # Avoids needing PIL plugins (pillow-heif / pillow-jxl) and preserves the
+    # codestream bit-for-bit. MP4/MOV/M4A are ISOBMFF too, so the same top-level
+    # uuid/jumb box walker applies. Route by suffix OR by an ``ftyp`` content
+    # sniff, so a correctly-shaped container is handled whatever its extension.
+    from remove_ai_watermarks.noai.isobmff import is_isobmff, strip_c2pa_boxes
 
+    with open(source_path, "rb") as f:
+        head = f.read(12)
+    if source_path.suffix.lower() in _ISOBMFF_EXTS or is_isobmff(head):
         data = source_path.read_bytes()
         cleaned, stripped = strip_c2pa_boxes(data)
         output_path.parent.mkdir(parents=True, exist_ok=True)
         output_path.write_bytes(cleaned)
-        logger.info("Stripped %d C2PA box(es) → %s", stripped, output_path)
+        logger.info("Stripped %d AI-provenance box(es) → %s", stripped, output_path)
         return output_path
 
+    # Containers we can detect (via identify's byte scan) but cannot strip at the
+    # container level: non-ISOBMFF audio/video (Matroska/WebM are EBML; MP3 is
+    # framed; WAV is RIFF). Re-encoding them is out of scope, so fail clearly
+    # rather than crash in the PIL image path below.
+    if source_path.suffix.lower() in _UNSUPPORTED_CONTAINER_EXTS:
+        raise ValueError(
+            f"container-level metadata removal is not supported for {source_path.suffix} "
+            "(detection via `identify` still works); re-encode it with a media tool to strip metadata"
+        )
+
     # Read image and filter metadata
     with Image.open(source_path) as img:
         img = img.copy()

src/remove_ai_watermarks/noai/c2pa.py

@@ -28,6 +28,7 @@ from remove_ai_watermarks.noai.constants import (
     C2PA_CHUNK_TYPE,
     C2PA_ISSUERS,
     C2PA_SIGNATURES,
+    C2PA_SOFT_BINDINGS,
     PNG_SIGNATURE,
     SYNTHID_C2PA_ISSUERS,
 )
@@ -174,6 +175,18 @@ def synthid_vendors_in(buffer: bytes) -> list[str]:
     return sorted({name for sig, name in C2PA_ISSUERS.items() if sig in buffer and sig in SYNTHID_C2PA_ISSUERS})
 
 
+def soft_binding_vendors_in(buffer: bytes) -> list[str]:
+    """Return forensic-watermark vendor names whose C2PA soft-binding ``alg``
+    identifier appears in ``buffer``.
+
+    A ``c2pa.soft-binding`` assertion names the watermark scheme that stamped the
+    pixels (Adobe TrustMark, Digimarc, Imatag, Steg.AI, ...). Shared by the PNG
+    caBX parser and the format-agnostic binary scan so both apply the same
+    C2PA_SOFT_BINDINGS rule against their respective bytes.
+    """
+    return sorted({name for sig, name in C2PA_SOFT_BINDINGS.items() if sig in buffer})
+
+
 def _parse_c2pa_chunk(chunk_data: bytes, c2pa_info: dict[str, Any]) -> None:
     """Parse C2PA chunk data and populate info dictionary."""
     c2pa_info["c2pa_manifest"] = f"C2PA manifest ({len(chunk_data)} bytes)"
@@ -238,6 +251,13 @@ def _parse_c2pa_chunk(chunk_data: bytes, c2pa_info: dict[str, Any]) -> None:
         c2pa_info["synthid_vendors"] = synthid_vendors
         c2pa_info["synthid_watermark"] = synthid_verdict(", ".join(synthid_vendors))
 
+    # Soft-binding: a forensic/third-party watermark vendor named in the
+    # manifest (Adobe TrustMark, Digimarc, ...), independent of the issuer.
+    soft_binding_vendors = soft_binding_vendors_in(chunk_data)
+    if soft_binding_vendors:
+        c2pa_info["soft_binding_vendors"] = soft_binding_vendors
+        c2pa_info["soft_binding"] = ", ".join(soft_binding_vendors)
+
 
 def extract_c2pa_chunk(image_path: Path) -> bytes | None:
     """

src/remove_ai_watermarks/noai/constants.py

@@ -122,6 +122,26 @@ C2PA_AI_TOOLS = {
     b"Firefly": "Firefly",
 }
 
+# C2PA ``c2pa.soft-binding`` algorithm identifiers -> the forensic-watermark
+# vendor that stamped the pixels. The manifest's ``alg`` field names the
+# watermark scheme even when the watermark itself cannot be decoded locally, so
+# a byte-scan for these (keyed on a distinctive prefix to catch all variants)
+# tells us a third-party forensic watermark is present and whose. Verified
+# against the official C2PA registry (github.com/c2pa-org/softbinding-algorithm-list).
+# Adobe TrustMark is additionally decodable locally (see ``trustmark_detector``);
+# the rest (Digimarc, Imatag, Steg.AI, etc.) are proprietary oracle-only decoders.
+C2PA_SOFT_BINDINGS = {
+    b"com.adobe.trustmark": "Adobe TrustMark",
+    b"com.digimarc": "Digimarc",
+    b"com.imatag.lamark": "Imatag (Lamark)",
+    b"ai.steg": "Steg.AI",
+    b"com.microsoft.invismark": "Microsoft InvisMark",
+    b"com.microsoft.wavmark": "Microsoft WavMark",
+    b"com.verimatrix": "Verimatrix",
+    b"com.nagra.nexguard": "NAGRA NexGuard",
+    b"com.aiwatermark": "AIWatermark",
+}
+
 # Lowercased substrings that mark an AI generator when found in an EXIF
 # ``Software`` / XMP ``CreatorTool`` value. Conservative on purpose: plain
 # editors like "Adobe Photoshop" or "GIMP" must NOT match (no AI token), so only

src/remove_ai_watermarks/noai/isobmff.py

@@ -23,13 +23,25 @@ from typing import TYPE_CHECKING
 if TYPE_CHECKING:
     from collections.abc import Iterator
 
-from remove_ai_watermarks.metadata import C2PA_UUID
+from remove_ai_watermarks.metadata import (
+    AIGC_MARKERS,
+    C2PA_UUID,
+    IPTC_AI_FIELD_MARKERS,
+    IPTC_AI_MARKERS,
+)
 
-# Top-level box types that carry C2PA payload. ``uuid`` boxes are checked
-# against ``C2PA_UUID`` before being stripped; ``jumb`` boxes are always
-# stripped (JPEG-XL uses them exclusively for JUMBF).
+# Top-level box types that may carry AI provenance. ``uuid`` boxes are checked
+# against ``C2PA_UUID`` / AI-label markers before being stripped; ``jumb`` boxes
+# are always stripped (JPEG-XL uses them exclusively for JUMBF).
 C2PA_BOX_TYPES: frozenset[bytes] = frozenset({b"uuid", b"jumb"})
 
+# AI-label byte markers (TC260 AIGC, IPTC "Made with AI", IPTC 2025.1 AI fields)
+# whose presence inside an XMP ``uuid`` box means the box carries an AI label.
+# Matching the payload rather than a fixed XMP UUID avoids the XMP-box UUID
+# byte-order ambiguity and stays surgical: only AI-bearing XMP is dropped, plain
+# XMP (copyright, camera info) is kept.
+_AI_LABEL_MARKERS: tuple[bytes, ...] = AIGC_MARKERS + IPTC_AI_MARKERS + IPTC_AI_FIELD_MARKERS
+
 
 def _iter_top_level_boxes(data: bytes) -> Iterator[tuple[int, int, bytes, int]]:
     """Yield ``(start, end, type, payload_offset)`` for each top-level box.
@@ -67,12 +79,22 @@ def is_isobmff(data: bytes) -> bool:
 
 
 def strip_c2pa_boxes(data: bytes) -> tuple[bytes, int]:
-    """Return ``(cleaned_bytes, stripped_count)``.
+    """Return ``(cleaned_bytes, stripped_count)`` with AI-provenance boxes removed.
 
-    Walks top-level boxes; drops any ``uuid`` box whose UUID equals
-    ``C2PA_UUID`` and any ``jumb`` box (JPEG-XL JUMBF container). All other
-    boxes are emitted verbatim. If the input is not ISOBMFF-shaped, returns
-    it unchanged.
+    Walks top-level boxes and drops:
+    - any ``uuid`` box whose UUID equals ``C2PA_UUID`` (a C2PA manifest);
+    - any ``uuid`` box whose payload carries an AI-label marker (an XMP packet
+      with a TC260 / IPTC / IPTC-2025.1 AI field -- caught by content, not by the
+      XMP UUID, so it works regardless of the UUID's byte order, and leaves plain
+      non-AI XMP intact);
+    - any ``jumb`` box (JPEG-XL JUMBF container).
+
+    All other boxes (incl. ``mdat`` / codestream) are emitted verbatim, so pixel
+    and audio data is preserved bit-for-bit. Non-ISOBMFF input is returned
+    unchanged. Despite the name this also covers MP4/MOV/M4A video and audio
+    (all ISOBMFF). NOTE: EXIF/XMP stored as *items inside the ``meta`` box*
+    (typical for AVIF/HEIF images) is not removed -- that needs meta-box surgery
+    and is a documented limitation.
     """
     if not is_isobmff(data):
         return data, 0
@@ -80,14 +102,15 @@ def strip_c2pa_boxes(data: bytes) -> tuple[bytes, int]:
     out = bytearray()
     stripped = 0
     for start, end, box_type, payload_off in _iter_top_level_boxes(data):
-        if box_type in C2PA_BOX_TYPES:
-            if box_type == b"uuid":
-                # uuid boxes carry the 16-byte UUID immediately after the type.
-                if payload_off + 16 <= end and data[payload_off : payload_off + 16] == C2PA_UUID:
-                    stripped += 1
-                    continue
-            else:  # b"jumb"
+        if box_type == b"uuid":
+            # uuid boxes carry the 16-byte UUID immediately after the type.
+            is_c2pa = payload_off + 16 <= end and data[payload_off : payload_off + 16] == C2PA_UUID
+            has_ai_label = any(marker in data[payload_off:end] for marker in _AI_LABEL_MARKERS)
+            if is_c2pa or has_ai_label:
                 stripped += 1
                 continue
+        elif box_type == b"jumb":
+            stripped += 1
+            continue
         out.extend(data[start:end])
     return bytes(out), stripped

src/remove_ai_watermarks/trustmark_detector.py

@@ -0,0 +1,72 @@
+"""Detect Adobe TrustMark invisible watermarks.
+
+TrustMark (github.com/adobe/trustmark, MIT) is the open, keyless image watermark
+behind Adobe "Durable Content Credentials": when a C2PA manifest is stripped, a
+TrustMark soft binding can still re-link the asset to its manifest in a
+repository. Unlike SynthID it has a PUBLIC decoder with no secret key, so a
+TrustMark-stamped image can be identified locally. Adobe's shipping products use
+Variant P (the ``com.adobe.trustmark.P`` soft-binding ``alg``); this wrapper
+loads that model.
+
+Optional dependency (extra: ``trustmark``); the model weights download on first
+use. ``detect_trustmark`` returns None when the package is absent. This detects
+provenance (Adobe Content Credentials), NOT AI generation as such -- TrustMark
+also marks human-authored content -- so callers should treat it as a watermark
+signal, not proof of AI origin.
+"""
+
+# trustmark ships no type stubs; relax untyped-library diagnostics for this thin
+# wrapper module only.
+# pyright: reportMissingTypeStubs=false, reportUnknownMemberType=false, reportUnknownVariableType=false, reportUnknownArgumentType=false, reportMissingImports=false
+
+from __future__ import annotations
+
+import logging
+from typing import TYPE_CHECKING, Any
+
+if TYPE_CHECKING:
+    from pathlib import Path
+
+log = logging.getLogger(__name__)
+
+# Adobe ships Variant P in production (com.adobe.trustmark.P).
+_MODEL_TYPE = "P"
+# Lazily constructed singleton -- model load + first-use download is expensive.
+_tm: Any = None
+
+
+def is_available() -> bool:
+    """True if the optional ``trustmark`` package is installed."""
+    import importlib.util
+
+    return importlib.util.find_spec("trustmark") is not None
+
+
+def _decoder() -> Any:
+    global _tm
+    if _tm is None:
+        from trustmark import TrustMark
+
+        _tm = TrustMark(verbose=False, model_type=_MODEL_TYPE)
+    return _tm
+
+
+def detect_trustmark(image_path: Path) -> str | None:
+    """Return a TrustMark scheme note if a TrustMark watermark is decoded, else None.
+
+    Returns e.g. ``"Adobe TrustMark (variant P, schema 0)"`` when the decoder
+    reports the watermark present, or None if it is absent, the optional
+    ``trustmark`` package is not installed, or the image cannot be read/decoded.
+    """
+    if not is_available():
+        return None
+    try:
+        from PIL import Image
+
+        with Image.open(image_path) as img:
+            cover = img.convert("RGB")
+        _wm_secret, wm_present, wm_schema = _decoder().decode(cover)
+    except Exception as exc:  # model download / decode failure / unreadable image
+        log.debug("TrustMark decode failed for %s: %s", image_path, exc)
+        return None
+    return f"Adobe TrustMark (variant {_MODEL_TYPE}, schema {wm_schema})" if wm_present else None