# Not All Challenges Are Equal: Evaluating Interactive Liveness Detection Against Real-Time Face Swaps

arXiv: https://arxiv.org/abs/2610.16417 · HTML: https://mlsanity.com/paper/2610.16417/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 10 of its 25 references that are in the map.
- First posted on arXiv 12 Oct 2026.

## Builds on (most cited first, 10 of 10)

- [MediaPipe: A Framework for Building Perception Pipelines](https://mlsanity.com/paper/1906.08172/) (2019)
- [Towards Universal Fake Image Detectors that Generalize Across Generative Models](https://mlsanity.com/paper/2302.10174/) (2023)
- [Detecting Deepfakes with Self-Blended Images](https://mlsanity.com/paper/2204.08376/) (2022)
- [UCF: Uncovering Common Features for Generalizable Deepfake Detection](https://mlsanity.com/paper/2304.13949/) (2023)
- [FakeCatcher: Detection of Synthetic Portrait Videos using Biological Signals](https://mlsanity.com/paper/1901.02212/) (2019)
- [DeepFaceLab: Integrated, flexible and extensible face-swapping framework](https://mlsanity.com/paper/2005.05535/) (2020)
- [Deepfake-Eval-2024: A Multi-Modal In-the-Wild Benchmark of Deepfakes Circulated in 2024](https://mlsanity.com/paper/2503.02857/) (2025)
- [Seeing is Living? Rethinking the Security of Facial Liveness Verification in the Deepfake Era](https://mlsanity.com/paper/2202.10673/) (2022)
- [GOTCHA: Real-Time Video Deepfake Detection via Challenge-Response](https://mlsanity.com/paper/2210.06186/) (2022)
- [DF-Captcha: A Deepfake Captcha for Preventing Fake Calls](https://mlsanity.com/paper/2208.08524/) (2022)

## Abstract (arXiv)

Remote identity verification assumes that a camera stream shows a live person, yet public real-time face-swap tools can replace that person before the stream reaches the verifier. Passive deepfake detectors generalize poorly to new generators, while interactive challenges are often selected without evidence of which gestures expose current attacks. We evaluate randomized gesture challenges in 108 live sessions with six subjects, 24 impersonated identities, and two face-swap tools, DeepFaceLive and FaceFusion, injected through a virtual camera. The static calibration segment reaches a session-level AUC of 0.878 with a frozen UCF spatial detector, while the mean across the active-gesture windows reaches 0.988. Pose and combined gestures have the highest point estimates, whereas expressions show no clear improvement. Hand occlusion against FaceFusion, configured with an occlusion mask, scores below the static baseline. The end-to-end time required to satisfy the validator also distinguishes attacks from genuine sessions, achieving a session-level AUC of 0.732, although this signal includes synthesis and transport delays. These results show that challenge sets should be tested against current attack configurations and that response time can provide an additional, deployment-specific signal.