pith. sign in
Pith Number

pith:JHERORN2

pith:2026:JHERORN27XK5HCFQY3GR6S35OC
not attested not anchored not stored refs pending

The Forensic Cost of Watermark Removal: From Dedicated Attacks to Image Editing

Ewa Kijak, Gautier Evennou

Watermark removal methods leave statistical artifacts that a classifier can detect at a false positive rate of one in a thousand.

arxiv:2604.25491 v2 · 2026-04-28 · cs.CV · cs.AI

Add to your LaTeX paper
\usepackage{pith}
\pithnumber{JHERORN27XK5HCFQY3GR6S35OC}

Prints a linked badge after your title and injects PDF metadata. Compiles on arXiv. Learn more · Embed verified badge

Record completeness

1 Bitcoin timestamp
2 Internet Archive
3 Author claim open · sign in to claim
4 Citations open
5 Replications open
Portable graph bundle live · download bundle · merged state
The bundle contains the canonical record plus signed events. A mirror can host it anywhere and recompute the same current state with the deterministic merge algorithm.

Claims

C1strongest claim

a modern classifier trained on these artifacts achieves state-of-the-art detection rates at 10^{-3} FPR across every removal method tested

C2weakest assumption

The statistical artifacts are inherent to the removal process itself rather than specific to the particular implementations, datasets, or training procedures used in the experiments.

C3one line summary

Watermark removal leaves statistical artifacts that allow classifiers to detect the attempt at 10^{-3} FPR across tested methods, establishing forensic stealthiness as a required property.

Receipt and verification
First computed 2026-05-28T02:04:48.259377Z
Builder pith-number-builder-2026-05-17-v1
Signature Pith Ed25519 (pith-v1-2026-05) · public key
Schema pith-number/v1.0

Canonical hash

49c91745bafdd5d388b0c6cd1f4b7d70ab625b937d85558c96affc8c3c5d9256

Aliases

arxiv: 2604.25491 · arxiv_version: 2604.25491v2 · doi: 10.48550/arxiv.2604.25491 · pith_short_12: JHERORN27XK5 · pith_short_16: JHERORN27XK5HCFQ · pith_short_8: JHERORN2
Agent API
Verify this Pith Number yourself
curl -sH 'Accept: application/ld+json' https://pith.science/pith/JHERORN27XK5HCFQY3GR6S35OC \
  | jq -c '.canonical_record' \
  | python3 -c "import sys,json,hashlib; b=json.dumps(json.loads(sys.stdin.read()), sort_keys=True, separators=(',',':'), ensure_ascii=False).encode(); print(hashlib.sha256(b).hexdigest())"
# expect: 49c91745bafdd5d388b0c6cd1f4b7d70ab625b937d85558c96affc8c3c5d9256
Canonical record JSON
{
  "metadata": {
    "abstract_canon_sha256": "01fb88f0d07868b00c0170ad54f8ae560e872ac8edf7a03850ccdc5b02108d5a",
    "cross_cats_sorted": [
      "cs.AI"
    ],
    "license": "http://creativecommons.org/licenses/by-nc-sa/4.0/",
    "primary_cat": "cs.CV",
    "submitted_at": "2026-04-28T10:47:21Z",
    "title_canon_sha256": "5422d409991473b970cc1011830cf94d2cfcf203616c450e8f6f701daee3ae0d"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2604.25491",
    "kind": "arxiv",
    "version": 2
  }
}