Image Deepfake Detection

Bynn Image Deepfake Detection

The Bynn Image Deepfake Detection model identifies face swaps in images: a photo or selfie frame in which the face has been replaced by a face-swapping tool. Built by Bynn for identity verification, it returns a clear decision, a probability and the face-swapping method the content most resembles.

The Challenge

Deepfake technology has democratized face manipulation. What once required Hollywood-level resources now runs on consumer hardware. Free tools replace a face in a photo or a live camera feed in seconds, with lighting, expression and head movement carried over from the real person in front of the camera.

The consequences are severe. Criminals create fake IDs using face-swapped photos. Romance scammers build profile pictures that pass casual inspection. KYC verification systems face manipulated selfies designed to match stolen identity documents. Financial fraud, account takeovers and synthetic identity creation all leverage face manipulation technology.

Detection is an arms race. Yesterday's detection methods fail against today's tools. Platforms need detection that is built for the content they actually receive and refreshed as new tools appear.

Model Overview

The Bynn Deepfake Detection model is Bynn's own face-swap detector, built for identity verification: it is designed for the selfie frames and videos real verification sessions produce, and it is kept current as new face-swapping tools appear. It returns a probability, a clear decision and the face-swapping method the content most resembles.

Achieving 99.8% accuracy, with 99.99% of face-swap attacks detected at a false reject rate of 0.32% on held-out verification sessions, it provides robust protection against face-swap attacks on identity verification and authentication flows.

How It Works

• Face analysis: the face in each frame is located and analyzed for the traces a face swap leaves behind
• Decision: the analysis yields a fake probability and a clear real or fake decision for the image
• Attribution: the response names the face-swapping method the content most resembles, for investigation and reporting

Request

Send one image with image_url or base64_image (JPEG, PNG or WebP, up to 20MB). Send the image as it was captured, without resizing or re-encoding it first. To analyze several frames of the same capture together, use Video Deepfake Detection with the recording.

Response Structure

The API returns a structured JSON response containing:

• label: String, "fake" or "real", or "unverifiable" when no face could be analyzed
• is_fake: Boolean, true when a face swap was detected; null when unverifiable
• is_real: Boolean, the inverse of is_fake; null when unverifiable
• fake_probability: Float (0.0 to 1.0), probability that the content is a face swap
• confidence: Float (0.0 to 1.0), the model's confidence in the returned label
• frames_total and frames_scored: Integer, always 1 for an image, and 1 or 0 depending on whether a face was analyzed
• swapper: String, the face-swapping method the content most resembles, "real" for real content
• frame_probabilities: Array with the image's fake probability, or null when no face was found

Example Response:

{
  "label": "fake",
  "is_fake": true,
  "is_real": false,
  "fake_probability": 0.998,
  "confidence": 0.998,
  "frames_total": 1,
  "frames_scored": 1,
  "swapper": "inswapper_128",
  "frame_probabilities": [0.998]
}
Code
Copy

Note: an "unverifiable" result means no face could be analyzed. Treat it as content to retry or review, not as evidence of a real person.

Performance Metrics

Use Cases

• KYC Verification: check the selfie frames of a verification session for a face swap before matching the face to the document
• Authentication Security: prevent face-swap attacks on facial recognition authentication
• Social Media and Dating Platforms: flag profile photos in which a real face was swapped
• Financial Services: screen customer photos for face swaps before account approval

Known Limitations

• Face swaps only: the model detects a real face that was replaced. Fully AI-generated faces are covered by AI-Generated Image Detection, and printed photos, masks and screen replays by Face Liveness Detection. Use them together for full coverage.
• One face per frame: the most prominent face is analyzed. Crop first if a specific face in a group matters.
• Image quality: very small, blurred or partially visible faces reduce reliability.
• Generator evolution: new face-swapping tools appear constantly; the model is updated as they do, and detection effectiveness should be monitored.

Disclaimers

This model provides a probability and a decision, not definitive proof of manipulation.

• Screening Tool: use it as part of a multi-layered verification strategy together with liveness, document checks and face matching, not as the sole decision factor
• Human Review: route flagged high-stakes decisions to a reviewer
• Not Legal Evidence: a probability is not a finding of fraud