// runnable playbook

deepfake investigation (video / audio / image)

face-swap, voice-clone, identity-impersonation. PRNU + GAN fingerprint + ELA + lip-sync + audio splice.

a guided path, not automation — each step opens a tool you run yourself; nothing uploads. progress is saved only in this browser.

// based on the curated pipeline

wraps the deepfake — image evidence kit preset — drop suspect images → AI provenance → face-swap artifacts → copy-move forgery → LSB/chi-square stego → report

methodology guide →worked example →full tool list + 4 more pipelines →

guided steps

0/7 done

01
evidence manifest generator
hash every image file before pixel analysis
open tool →methodology
your note (local only)
02
ai generated image provenance analyzer
model / generator fingerprint hints from metadata and artifact patterns
open tool →methodology
your note (local only)
03
gan fingerprint detector
FFT grid periodicity + histogram anomalies — synthetic image screener
open tool →methodology
your note (local only)
04
face swap artifact detector
boundary and blending artifacts around swapped facial regions
open tool →methodology
your note (local only)
05
copy-move forgery detector
cloned-region detection — common in composite fakes
open tool →methodology
your note (local only)
06
image steganography detector
chi-square / RS / LSB analysis on decoded pixels
open tool →methodology
your note (local only)
07
case report generator
draft a report suitable for legal review of still-image authenticity
suggested options · title: deepfake — image evidence assessment
open tool →methodology
your note (local only)

when you're done

export a run summary — a small JSON record of which steps you marked done, your notes, and a self-hash so the record can't be silently altered. it is your reproducibility note, not a per-tool receipt: each tool emits its own input→output receipt when you run it.