VestigeForensics

— Image forensics · calibrated verdicts

Forensic-grade AI image detection.

A detector fine-tuned for current generators scores your image and returns a verdict at a capped false-positive rate — 5% for triage, 1% for evidence — with thresholds calibrated per condition and every limit stated on the report, not buried in a footnote.

Scored in memory · never stored · verified chain of custody

Forensic report

VF-9E41C7A2

AI-flagged · strict ≤1% FPR
0.941primary · calibrated

thr 0.725 @ ≤1% fpr · detection rate 43% under social chain

Community Forensics — VF fine-tune
0.941
Community Forensics (stock)
0.212
SDXL Detector
0.716

primary + supporting signals · robustness panel · limits

sha256 9e41c7a2d05b8f…9c77open sample →

8,064

benchmark images

8

real-world conditions

386,072

scored evaluations

6

detectors on the calibration grid

How it works

Three steps between an image and a defensible answer

01 · Hash

Fingerprinted in your browser

Your browser computes the SHA-256 of the exact bytes before upload. The returned report must hash the identical bytes or the client rejects it — chain of custody is enforced, not just printed.

02 · Score

A calibrated primary, corroborated

A peer-reviewed detector (CVPR 2025 lineage), fine-tuned on 2024–26 generators and pinned by checkpoint hash, drives the verdict; independent supporting signals corroborate it.

03 · Decide

A verdict with a false-positive budget

Thresholds are calibrated so at most 5% — or 1% — of real photos would be flagged. The report states detection power under your image's condition.

Why Vestige

Confidence, including its limits

Detection tools love to quote lab-bench numbers. We publish what survives contact with reality — recompression, messenger re-encodes, screenshots of screenshots.

  • The same detector that scores 0.93 AUC catches ~55% of AI images under a social-media re-encode chain when false positives are capped at 5% — and ~43% at the strict 1% standard.
  • No tool on the market clears the ~90% evidentiary gate under realistic conditions. Anyone implying otherwise is selling you a liability.
  • So every report quantifies exactly what a flag — or its absence — is worth for your image, under its estimated condition. That number is your defensible ground.
0%25%50%75%100%64%Clean61%JPEG q7062%JPEG q5061%Resize 50%55%WhatsApp60%Screenshot55%Social chain≈90% evidentiary decision gateheadline AUC 0.93 — same run, same detector
share of AI images caught at ≤5% false positives on every real source · fine-tuned primary detector · run full_v4 (8,064 images) · social chain = screenshot of a WhatsApp image

Who it's for

Built for the lab. Useful far beyond it.

The report

Every claim on it is auditable

SHA-256 of the exact bytes analyzed. Thresholds tied to a named calibration run. A hash of the report itself. Built to be attached to a case file, not a slide deck.

Privacy, in three commitments

  • Your image is scored in memory and discarded — never written to disk, never logged, never kept.
  • Chain of custody is enforced: your browser hashes the bytes before upload and rejects any report that hashed different bytes.
  • There is nothing to delete server-side. The report is returned to you and exists only where you keep it.

Read the privacy commitments →

FAQ

Fair questions, straight answers

Can you tell me definitively whether an image is AI?+

No — and be suspicious of anyone who says yes. We return a calibrated statistical verdict at a false-positive rate you choose, with the detection rate and every known limit printed on the report. That is the strongest honest claim current science supports.

What kinds of images work?+

JPEG, PNG, and WebP. Re-shared, recompressed, screenshotted images are exactly what the pipeline is calibrated for — our benchmark includes a “screenshot of a WhatsApp image” condition because that is what real cases look like.

Do you keep my images?+

No. Your image is scored in memory and discarded — it is never written to disk, never logged, and never used for training. The report is returned to you and exists only where you keep it.

What does the free analysis include?+

The complete forensic report — calibrated verdict, primary and supporting detector scores, robustness panel, limits, and chain-of-custody hashes. One image per account, then pay-per-image credits or an API plan.

Analyze your first image free

Create an account, upload one image, and read the full forensic report — thresholds, limits, hashes and all. No card required.