# Pulse-based deepfake detectors mostly spot flicker and video source, not heartbeats

A preprint finds that deepfake detectors built to read a heartbeat from facial skin colour mainly pick up frame-to-frame colour flicker. They also learn which collection a video came from. Common benchmark splits can hide this.

- Category: Safety & evaluation
- Readiness level: II (Benchmarked) on Science Underway's four-step scale, as proposed
- Published: 2026-11-12
- Editor: Stefan Perdal
- URL: https://scienceunderway.com/articles/pulse-based-deepfake-detectors-mostly-spot-flicker-and-video-source-not-heartbea

## The study

Pulse or Provenance? What rPPG-Based Deepfake Detectors Learn (preprint, not peer reviewed). DOI 10.48550/arxiv.2611.13992, arXiv 2611.13992. https://arxiv.org/abs/2611.13992

## At a glance

- What it shows: Some deepfake detectors claim to work by finding a heartbeat in a face, which fakes should lack. This study finds they mostly detect rapid colour flicker that video generators add. They also learn which collection a video came from, so they flag real footage from elsewhere as fake.
- What it does not show: It does not show that fake videos never contain a pulse, or that every published pulse-based detector fails. It tests the authors' own copies of these detectors on two public datasets, and it has not been peer reviewed.
- Why it matters: A detector that flags real footage as fake because it came from an unfamiliar camera or platform produces false alarms. In journalism, courts or content moderation, that could discredit genuine evidence.

## What the study shows

Remote photoplethysmography (rPPG) reads tiny colour changes in facial skin caused by blood flow. Several deepfake detectors rely on it. Their premise is simple: a synthetic face has no blood flow, so it should have no pulse. The authors test what these detectors actually pick up. They use Celeb-DF++, a public benchmark with 22 forgery methods, and FaceForensics++ (FF++), an older benchmark. Each real and fake video gives exactly one window: its first 160 frames.

The authors report that on talking-face fakes, where a still photo is animated from audio, a crude colour signal from the face almost perfectly separates real from fake. Its AUC is 0.998. AUC is a score where 1.0 is perfect and 0.5 is a coin toss. A dedicated pulse-extraction model scores only about 0.87. If the cue were a heartbeat, the better pulse estimator should win.

The face turns out not to matter. On talking-face and face-reenactment fakes, a patch of background, or the whole frame with no face detection, works as well as the face. The useful information sits above the normal heart-rate range. Shuffling the order of frames destroys it. The cue is how colour changes from one frame to the next.

Targeted edits confirm this. Filtering out fast colour changes made 97% of fakes look real to the detectors. Adding fake-like fast changes to real videos made almost all of them look fake. Adding an artificial pulse to fakes made almost no difference. The cue also survived matching frame rate, codec and resolution between real and fake videos.

To find the source, the authors regenerated real videos from themselves with two face-animation tools. Animating a face from a single frame added the same flicker, and the fakes became separable from their own originals. Rebuilding each frame from itself did not add it. This second control was run with one tool only.

The detectors also learned video source. Trained on Celeb-DF++, colour-based detectors called over 99% of real FF++ videos fake. A general-purpose detector built on CLIP, an image model trained on pictures paired with captions, called most of them fake too. Adding pulse features to CLIP did not improve it.

Finally, the official Celeb-DF and Celeb-DF++ test lists share people and source videos with the training data. In one custom protocol, reusing test videos in training raised a weak detector's score by about 0.30 AUC. A strong detector gained only about 0.05.

## Our reading

In our reading, this is a careful audit, not a new detector. Its main value is the set of controls. The authors test a background patch, shuffled frames, separate frequency bands and identical encoding. They also run an independent reimplementation with no shared code. Together these make the conclusion hard to dismiss. A detector justified by biology is largely detecting a rendering artefact and a dataset fingerprint.

The practical risk is false alarms. Suppose a newsroom uses such a detector to check a genuine clip from a phone or a platform it never saw in training. On this evidence, the tool could label that clip fake with high confidence. The FF++ result is exactly this case: real videos, scored almost uniformly as fake.

It is also notable that part of the critique targets the authors' own earlier pulse-based work. The paper is a preprint and has not been peer reviewed. On our four-level readiness scale it sits at level II, benchmarked: results are on public benchmarks. Code and evaluation splits are promised but not yet released, so it does not reach level III.

The rest of the article (what it means, limits, what to watch) is free for members: https://scienceunderway.com/articles/pulse-based-deepfake-detectors-mostly-spot-flicker-and-video-source-not-heartbea

## How this was made

An AI model read the study and wrote this article in the structure Science Underway uses. An editor reviewed it and approved it for publication. Check the original study before you rely on the details.

---
Source: Science Underway, https://scienceunderway.com/. Please link to the article when you cite it.
