Skip to content
ExiphoreRequest a demo

Synthetic media forensics

Uncover what’s not real.

Forensic examination of video, images, voice, text and documents — with measurements, stated limits and a signed report.

Identity redacted
Examination · EXI/2026/0004/E001Video exhibit
Manipulation indicated
0.74 manipulation index

Interval 0.59–0.88 · Quality ceiling 57% · 13 of 14 signals used

Physiological41.3%
Frequency29.1%
Temporal27.7%
Metadata1.9%
47.3 s · 360 × 444Examiner review required

A circulated video of a serving officer, Jantar Mantar, New Delhi — examined October 2026. Exhibit redacted; figures from the published case study.

Built forPolice and cyber crimeForensic laboratoriesIntelligenceFinancial crimeProsecution

The deliverable

A record you can sign and defend.

A finding on its own is a number. What leaves the platform is a record an examiner can sign and another expert can interrogate.

Product demo · recorded in the platform1:31

Examination result

Manipulated, authentic or inconclusive — with the interval that bounds it.

Evidence breakdown

Which families of evidence contributed to the finding, and by how much.

Confidence and ceiling

How far the exhibit itself allowed the examination to go.

Chain of custody

Hash, timestamps and custody events, each linked to the one before.

Examiner review

A named examiner's reasoning, recorded before release.

Sealed report

The complete record, downloadable and tamper-evident.

Every exhibit is now a question. We can help.

A face and a voice can be generated in minutes, well enough to pass a video call and well enough to reach a case file. Investigators are being handed media they cannot vouch for, and defences are claiming the same of media that is genuine.

65%report deepfake attacksOrganisations in India, February 20261
Growth in deepfake fraud, Q1 2025 vs Q1 2024Sumsub platform data2
8 million

deepfakes estimated to be shared in 2025, up from 500,000 in 2023.3

62%

of organisations hit by a deepfake attack in the past twelve months.4

1 in 4

job candidates worldwide projected to be fake by 2028.5

The platform

The Exiphore Media Trust Platform

One examination record for every kind of exhibit — each signal reported with what it can, and cannot, establish.

Explore the platform
Exhibit · circulated video of a serving officer, identity redactedIdentity redacted
4 REGIONS · INDEPENDENT RATES

Exhibit · circulated video of a serving officer, identity redacted

Measured result

A face that no single heart is driving

Light reflected from skin changes with every heartbeat. Exiphore recovers that pulse separately from four regions of the same face — forehead, both cheeks, chin. On a real face they agree, because one heart drives all four. On a synthesised face they do not.

  • Pulse coherence across facial regions
  • Blink dynamics
  • Lip-sync consistency
  • Temporal flow

Pulse recovered independently from four facial regions disagreed: 98, 61, 48 and 100 bpm. A face perfused by one heart does not disagree with itself.

What it cannot tell youPulse recovery needs a face large enough and stable enough to measure. Below roughly 100 pixels, or under heavy compression, the signal degrades and the examination says so rather than guessing.

New · Document forensics

Every edit leaves a trace.

Bank statements, invoices, contracts — as PDFs, Word files, scans or phone photos. Exiphore recovers the value a figure replaced, the clause the page hides and the total that no longer adds up, and draws each finding on the page.

10
independent document checks
5
questions, answered separately
4
formats, including scans and photos
Measured resultSynthetic test invoice
  1. Four independent checksOne altered figure

From the record

No examination of this file could have returned a higher confidence, whatever it found. A platform that reported 95% on this exhibit would be lying to you.

Technical case studyDelhi Police exhibit, October 2026
Read the case study
1 / 2
20 signalsacross 8 independent families of evidence; 13 applied to the recorded exhibit.
27.9 swall-clock time for the deep examination profile.
Air-gappedor on-premises. Evidence never leaves your estate.

Your environment

Sensitive evidence. Your infrastructure.

Run examinations within your own environment. Choose a deployment that fits your agency’s operational requirements.

  • On-premises
  • Private cloud
  • Air-gapped
Deployment & security details

FAQ

Deepfake detection, answered.

Validation & limitations
What is Exiphore?

Exiphore is a forensic deepfake detection and synthetic media forensics platform. It examines video, images, audio, documents and text for AI generation and manipulation, then produces a signed examination report with chain of custody. It runs on your own servers, including air-gapped networks. Exiphore is an AI Anytime product, built in Hyderabad, India.

What is the best deepfake detector for police and forensic investigators?

For casework, the best deepfake detector is the one whose findings survive challenge: it states its method and limits, keeps chain of custody, reports a confidence interval rather than a bare score, allows an inconclusive result and runs where the evidence is allowed to go. Exiphore is built to those criteria. Test any tool on exhibits from your own cases before relying on it.

How does Exiphore detect deepfakes?

Twenty measurements across eight independent families of evidence: physiological signals such as the pulse recovered from four regions of a face, frequency and generator fingerprints, temporal and lip-sync coherence, compression artefacts, metadata and content provenance. Most are signal measurements rather than machine learning, so each result can be explained to a reviewer.

What are Exiphore’s digital forensics AI agents?

Eight examination agents each measure the exhibit independently, with no shared state, so agreement between them means something. An adjudication step pools correlated signals into one finding with an interval and a quality ceiling. A named human examiner then reviews and signs it. The agents measure; the examiner decides.

Can Exiphore detect AI-generated images, voice clones and forged documents?

Yes. Exiphore examines face-swapped and lip-synced video, generated and edited images, cloned voices and synthetic speech, and altered PDFs and scanned documents. Model-generated text can be screened too, but text results are triage only and are labelled that way.

Can Exiphore detect an edited PDF or a fake bank statement?

Yes. Exiphore recovers earlier versions saved inside a PDF, compares what the page shows with what the file holds, checks each line's typography, and reconciles totals, tax, balances and dates — on PDFs, Word files and scanned or photographed pages. Each finding is drawn on the page with the value it replaced.

Is a deepfake detection report admissible as evidence in court?

Admissibility is for the court and counsel to decide. Exiphore is built to support it: the original is hashed (SHA-256) and sealed on intake, every action is recorded in a hash-chained custody log, each measurement states what it cannot establish, and a named examiner signs the finding. The hash values support certification of electronic records under Section 63 of the Bharatiya Sakshya Adhiniyam, 2023.

Can deepfake detection run on-premises or in an air-gapped network?

Yes. Exiphore runs on-premises, in a private cloud or fully air-gapped, on standard servers without GPUs. No exhibit, model call or telemetry leaves the network. The only optional component that can call an external model writes the plain-language summary; it never sees a measurement and can be switched off.

How accurate is Exiphore’s deepfake detection?

Performance depends on media quality, compression and the manipulation involved, so a single accuracy figure is not a guarantee for your casework. Every finding reports its confidence interval and the ceiling the exhibit’s quality imposes. Our published validation states its sample and limits; the best test is a pilot on exhibits from your own closed cases.

What happens when a deepfake examination is inconclusive?

Inconclusive is a reported outcome, not a failure. Exiphore shows which evidence conflicted or was too degraded, so an examiner can seek the original file, gather more context or record the limits of the examination instead of forcing a verdict.

Can Exiphore check Microsoft Teams calls and video-KYC for deepfakes?

Recorded meetings, call recordings and video-KYC captures can be examined as exhibits today, for executive impersonation, payment fraud and onboarding abuse. A direct Microsoft Teams connector is scoped work, described in our meeting-recordings case study.

Media trust isn’t optional⁠—⁠it’s evidence.

Take the first step toward exhibits you can stand behind. Book a guided demonstration with your use case in mind.

Schedule a demo

  • A walkthrough with your use case in mind
  • A frank discussion of capabilities and limitations
  • Deployment options for your environment
contact@exiphore.com

We reply within one working day. Privacy policy

Sources
  1. Thales, India survey (February 2026)
  2. Sumsub, Q1 2025 vs Q1 2024 platform data (June 2025)
  3. UK Government estimate, cited by Sumsub (2025)
  4. Gartner (September 2025)
  5. Gartner (2025)

Figures as published by the named sources. Exiphore does not generate threat statistics of its own, and does not present other people's research as product evidence — our measured performance is published separately, with its method.