If an image has no detectable invisible watermark, is it human-made, and if it has one, does that prove who made it?
No to both, on the papers read. Absence of a watermark is weak evidence: regeneration attacks removed pixel-level watermarks in over 99 percent of cases (Zhao et al.) and Stable Signature almost entirely (WAVES), and a generator may not mark its output at all. Presence is also not proof: one paper shows real images can be made to read as watermarked using a marked noise image, and the better-resisting schemes still have attack settings that work. What a vendor says it marks is in C3-B033-G12-08 and C3-B046-G16-07; this candidate covers the independent tests.
No to both, on the papers read. Absence of a watermark is weak evidence: regeneration attacks removed pixel-level watermarks in over 99 percent of cases (Zhao et al.) and Stable Signature almost entirely (WAVES), and a generator may not mark its output at all. Presence is also not proof: one paper shows real images can be made to read as watermarked using a marked noise image, and the better-resisting schemes still have attack settings that work. What a vendor says it marks is in C3-B033-G12-08 and C3-B046-G16-07; this candidate covers the independent tests.
Curator qualifications: The no-to-both answer follows from the verified removal and spoofing results. It is a synthesis across papers and is labelled so.
Evidence status: curator/producer inference or synthesis from the cited sources (code read, not executed, where code is cited); correlated desk review (Claude); not independently reviewed.
Structured fields
{
"citations": [
{
"url": "https://arxiv.org/abs/2306.01953v3",
"note": "results; Table 2; attack table; benchmark comparison; spoofing"
},
{
"url": "https://arxiv.org/abs/2401.08573v3",
"note": "results; Table 2; attack table; benchmark comparison; spoofing"
},
{
"url": "https://arxiv.org/abs/2310.00076v2",
"note": "results; Table 2; attack table; benchmark comparison; spoofing"
}
]
}Evidence claims
- [inference] No to both, on the papers read. Absence of a watermark is weak evidence: regeneration attacks removed pixel-level watermarks in over 99 percent of cases (Zhao et al.) and Stable Signature almost entirely (WAVES), and a generator may not mark its output at all. Presence is also not proof: one paper shows real images can be made to read as watermarked using a marked noise image, and the better-resisting schemes still have attack settings that work. What a vendor says it marks is in C3-B033-G12-08 and C3-B046-G16-07; this candidate covers the independent tests. · locator: results; Table 2; attack table; benchmark comparison; spoofing source
Rights
| component | license | hosting | redistribution | modification | training | Evidence and notes |
|---|---|---|---|---|---|---|
| documentation | unknown | permitted | permitted | unknown | unknown | Applies to this original summary only, not to the cited sources. |