DEEPCHECK - v1.0

Preliminary forensic visual screening for visible image-generation and manipulation indicators.

DISCLAIMER
This AI-assisted preliminary forensic screen cannot authenticate provenance, prove authenticity or manipulation, or replace qualified human examination. UPLOADED IMAGES ARE PROCESSED BY THE SERVER-SIDE ANALYSIS SERVICE.

KEEP THE RESEARCH MOVING

Independent checks, transparent limits, and future research updates. Support channels will be announced publicly.

Three free checks per browser each day. No account required.

Choose or drop a JPEG, PNG, or WebP image (maximum 8 MB / 20 MP)

HOW IT WORKS

The result is organized as localized visual evidence, not a final authenticity decision.

BETA
  1. 01VISUAL REVIEW

    Multimodal reasoning reviews visible consistency across anatomy, texture, lighting, reflections, geometry, typography, and object boundaries.

  2. 02LOCALIZED TARGETS

    Relevant observations are mapped to normalized image coordinates and displayed as Target boxes.

  3. 03EVIDENCE SUMMARY

    Each Target describes the visible evidence, why it matters, and the limits of the interpretation.

  4. 04BETA BOUNDARY

    The screen does not verify metadata or provenance and does not establish authenticity.

PRELIMINARY SCREENING REPORT

STATUS: READY DAILY LIMIT: 3 CHECKS
SYSTEM TIME · WITA
SCREENING SCOPE

Reviews visible consistency in structure, lighting, geometry, text, and object boundaries. It does not inspect provenance records or establish authenticity.

PUBLIC BETA ROADMAP

We are building this in public: calibrate image checks first, then publish non-sensitive research updates.

IN PROGRESS
  1. NOW · PUBLIC BETAThree no-account checks, visible limits, and abuse safeguards.
  2. NEXT · TRANSPARENCYPublish methodology and evaluation summaries without exposing private systems.
  3. LATER · COLLABORATIONConsider research and commercial pilots only after calibration and review.