Guide

Deepfake detection: how to spot synthetic media without overreacting

Deepfakes are not just strange videos on the internet anymore. They can appear in documents, images, voice notes, screenshots, and claims shared out of context. The safest response is to preserve the file, check the evidence, and verify the story another way.

By Stipple Research13 min readUpdated 16 July 2026
Key takeaways
  • Deepfake is a broad word. It can mean generated images, face swaps, voice clones, edited video, or synthetic documents.
  • A genuine file can still be used with a false caption or misleading context.
  • Detection works best when it combines technical checks, provenance, source review, and real-world confirmation.
  • Stipple currently focuses on uploaded images and documents, not general video or audio deepfake detection.
Evidence path
  1. 01

    Pause

    Start with the material.

  2. 02

    Preserve

    Add one more signal.

  3. 03

    Inspect

    Add one more signal.

  4. 04

    Corroborate

    Add one more signal.

  5. 05

    Respond

    Make a careful call.

01

What is a deepfake?

Short answer

A deepfake is media made or changed with AI so it appears to show a person, voice, object, place, or event that may not be real.

People often use deepfake to mean face-swap videos, but the problem is wider now. Synthetic media can include AI-generated images, fake profile photos, voice clones, edited screenshots, manipulated documents, and videos with altered speech.

Not every AI edit is harmful. A film effect, translation dub, or creative image may be fine. The risk appears when the media is used to mislead, impersonate, defraud, harass, or manufacture evidence.

02

What types of synthetic media should you know?

Different deepfake formats need different checks. A video detector will not automatically solve a fake invoice, and an image provenance check will not tell you whether a voice note is cloned.

TypeWhat it isCommon risk
Generated imageA picture made by an AI image model.Fake events, fake products, fake people.
Face swapOne face mapped onto another person's body or performance.Impersonation or non-consensual imagery.
Lip-sync editMouth movement changed to match different speech.Fabricated statements.
Voice cloneSynthetic audio made to sound like a real person.Payment fraud or impersonation.
AI inpaintingOnly part of an image is replaced or generated.Subtle evidence manipulation.
Synthetic documentFake layout, text, signature, image, or attachment.Fraudulent applications, claims, or onboarding.
03

Why does deepfake detection matter?

The harm usually comes from a decision. Someone pays an invoice, approves an application, publishes a story, hires a candidate, shares a rumour, or believes a person said something they did not say.

That is why the goal is not only to ask is this AI? The better question is: what decision is this media trying to influence, and what evidence would we need before trusting it?

04

How does deepfake detection work?

A deepfake detector may examine faces, motion, audio patterns, file metadata, provenance credentials, pixel-level signals, or document structure. The useful method depends on the file you actually have.

MediaUseful checksCommon complication
ImageProvenance, metadata, pixel signals, source search.Screenshots and recompression.
VideoFrame consistency, motion, audio-video sync, encoding traces.Low quality clips and platform transcodes.
AudioSpectral patterns, voice behaviour, source confirmation.Noise, codecs, and very short clips.
DocumentMetadata, layout, fonts, arithmetic, entities, provenance.Mixed genuine and fabricated parts.
05

Detection, provenance, and verification are not the same

This distinction helps people avoid bad conclusions. Detection asks whether the file resembles synthetic or manipulated media. Provenance asks what origin or edit history is recorded. Verification asks whether the claim being made is true.

ApproachQuestion it answersExample
DetectionDoes this look generated or manipulated?A face swap detector flags a video.
ProvenanceWhat origin or edits are recorded?A file has signed AI-generation credentials.
VerificationDid the event or claim actually happen?The person confirms through a known phone number.
06

What should you do if you suspect a deepfake?

The first move is to pause. Do not send money, publish, accuse, approve, or reject based on a suspicious file alone.

StepWhat to do
Preserve evidenceSave the original file, URL, account, timestamps, and message context.
Use the right checkerMatch the tool to the file type: image, document, video, or audio.
Check provenanceLook for origin records or missing/stripped evidence.
Verify another wayContact the claimed person or organisation through a trusted channel.
Corroborate contextLook for earlier copies, reports, records, or independent witnesses.
Escalate carefullyReport fraud, abuse, or safety threats through the right channel.
07

What can Stipple check today?

Stipple inspects uploaded images and documents for provenance, AI-generation indicators, editing and tampering traces, and, in supported document workflows, internal consistency.

Stipple does not present itself as a general video or audio deepfake detector. That narrower claim matters. A trustworthy product should tell you what it checks and what it does not.

Questions

Frequently asked questions

What is the difference between a deepfake and synthetic media?

Synthetic media is the broader term. Deepfake usually refers to convincing AI-made or AI-altered media involving a person, voice, identity, or event.

Can deepfakes always be detected?

No. Detection tools age as generation methods improve. Provenance and independent verification reduce the risk of relying on one classifier.

Can Stipple detect video or audio deepfakes?

Not as a general video or audio service today. Stipple currently focuses on uploaded images and documents.

Sources

Sources and further reading

  1. 01C2PA technical specification
  2. 02Content Authenticity Initiative
  3. 03NIST Open Media Forensics Challenge
  4. 04Europol: law enforcement and deepfakes

Educational guidance, not a forensic certification. Detection technologies and standards change; review material decisions against current evidence.

Start with the file in front of you

Upload an image or document for an evidence-backed review of provenance, synthetic indicators, editing traces, and inconsistencies.

Inspect an image or document