CORROBORATE
CORROBORATE
Try Live PoCInspector
All Research Whitepapers
Methodology
August 2026 5 min read

From Audio-Visual Deepfakes to Web Biometrics

Adapting self-supervised dissonance detection (Chugh et al., Feng et al.) to web sessions

Executive Summary

How CORROBORATE borrows the 'train-on-genuine-only' segment-then-aggregate structure from audio-visual deepfake forensics to prevent overfitting to attack generators.

1. The Trap of Supervised Classifiers

When security researchers train a classifier on specific attack samples, the model often overfits to quirks of the attack generator rather than learning genuine human behavior.

[!NOTE] Attackers evolve their generator parameters constantly. A defense that models specific attack signatures becomes obsolete the moment the attacker modifies their retiming script.


2. The Self-Supervised Paradigm

In audio-visual forensics:

  • Chugh et al. (ACM MM 2020 - Modality Dissonance Score): Evaluates whether audio track phonemes synchronize with video lip movements.
  • Feng et al. (CVPR 2023): Proved that synchrony can be learned exclusively from unmanipulated genuine videos without ever seeing a deepfake.

3. Self-Supervised Calibration in CMCC

CORROBORATE adapts this methodology to web dynamics:

  • The CMCC engine is calibrated solely against genuine human sessions ($A_0$).
  • Per-window coherence is scored against normal human variance.
  • When coherence falls below a calibrated rolling threshold for 2+ consecutive windows, a seam is flagged.