Demo

A direct walkthrough of the verification flow.

Demo scope

This page shows the review flow: inspect media, run detection, and read UID, confidence, and evidence output.

For implementation detail, request a technical walkthrough with your own media.

See it. Verify it.

Compare original vs watermarked media across image, video, and audio.

- Compare original and watermarked image samples.
- The watermark stays invisible; evidence appears in decode output.
- Built for fast operator review.

Before vs after watermark image comparison

⇄

Before (original)

After (watermarked)

Text + code preview

Text, docs, and code watermarking

DeadMark is expanding beyond image/video/audio with one API and format-aware profiles for text workflows. The target is practical survivability through copy/paste, spacing changes, and light reformatting.

Text detection preview

ChatGPT sample (demo)

"Daily operations update: all three service regions are stable after maintenance. Throughput is back to normal and alert volume remains low."

Detection overlay: UID DMK-TXT-7D1A-29F4 * confidence 96.8% * integrity 92 / 100 * recovery: spacing-normalized path.

Messaging

Chat apps, short posts, comments

Plain text

TXT, Markdown, structured text

Documents

DOCX, PDF text layers, exports

Code

Repositories, snippets, generated files

Code detection preview

Claude Code sample (demo)

export function scoreRisk(input: string): number {
  const normalized = normalizeText(input);
  const entropy = estimateEntropy(normalized);
  return Math.min(100, Math.round(entropy * 37));
}

Detection overlay: UID DMK-CODE-11C8-5AE2 * confidence 97.2% * integrity 94 / 100 * recovery: structure-preserved path.

Output model: present / uid / confidence / recovery status.

AI-origin estimation (no watermark, media) - Deep Scan in development

Model-signal attribution

Media-generation signal hints

Diffusion residual texture patternHigh

Temporal synthesis cadence patternMedium

Generative audio texture patternMedium

Model confidence

DALL-E family82%

Kling family74%

Seedance family69%

Deep Scan no-watermark attribution is media-focused (image, video, audio). This block is model-family confidence output, not watermark decode output.

Survival test results

Snapshot of demo survivability metrics across common transforms and platform-style delivery paths.

Attack resistance

Attack	Survival	Health After
JPEG Q70	✅	82.1%
JPEG Q50	✅	71.3%
Resize 75%	✅	78.9%
Resize 50%	✅	65.2%
Crop 10%	✅	89.4%
Gaussian Noise	✅	76.8%
Gaussian Blur	✅	84.2%
MP3 128kbps	✅	68.5%
AAC 128kbps	✅	72.1%
H.264 CRF23	✅	75.3%
Combined	✅	58.1%

Platform survivability

Platform	Image	Audio	Video
TikTok	89%	76%	72%
Instagram	91%	N/A	68%
YouTube	94%	85%	81%
Spotify	N/A	88%	N/A
Twitter/X	87%	74%	69%

These figures are based on controlled simulation runs across 1,000+ media samples designed to approximate real-world transformations. Field performance can vary depending on content characteristics, platform processing changes, and downstream recompression.