# Catching Lies Without Sending the Video: Privacy-Preserving Multimodal Deception Detection

arXiv: https://arxiv.org/abs/2606.22699 · HTML: https://mlsanity.com/paper/2606.22699/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 2 of its 7 references that are in the map.
- First posted on arXiv 21 Jun 2026.

## Builds on (most cited first, 2 of 2)

- [Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context](https://mlsanity.com/paper/2403.05530/) (2024)
- [Audio-Visual Deception Detection: DOLOS Dataset and Parameter-Efficient Crossmodal Learning](https://mlsanity.com/paper/2303.12745/) (2023)

## Abstract (arXiv)

Frontier multimodal models can guess whether a person is lying from a testimony video. To do so, they stream that raw face and voice to a third-party model. We ask whether the heavy media is needed at all. On the Real-life Trial Deception dataset, Whissle on-device speech and vision stack extracts a compact digest: transcript, emotion, age, gender, intent distributions, a deception intent filter, fluency and rhythm, per-frame facial behaviour, and prosody. Under speaker-independent evaluation, we report three findings. A small classifier on this digest reaches AUC 0.741, matching Gemini 2.5 Pro on full video. Handing the digest to a frontier LLM reaches AUC 0.755 with Claude Opus 4.8 at 7.8X fewer input tokens, with no media leaving the device. The reported 75% accuracy is a speaker-leakage artifact. We release code and experiments.