cs.CVNov 11, 2026

Paired Geometric Supervision for Generalizable Deepfake Detection

Authors: Luke Collins, Chang-Tsun Li, Duc Thanh Nguyen, Victor Sanchez

Organizations: School of Information Technology Deakin University Waurn Ponds, Australia · Department of Computer Science University of Warwick Coventry, UK · Universitat Autònoma de Barcelona, Spain, as a Distinguished Researcher

Abstract

We present OrthoPairGTL, a geometric training framework for cross-domain deepfake detection, built on a partially frozen DINOv3 backbone (∼\sim300M parameters), and make three contributions: (1) We re-evaluate six recent transfer-learning detectors (Forensics Adapter, Effort, three GenD variants and FakeSTormer) using the authors' released checkpoints under a single preprocessing pipeline across 17 cross-domain datasets (2018-2025), so that the reported gaps reflect method rather than per-method pipeline tuning. (2) We model the transformation between paired real and fake samples, training Parameter-Efficient Fine-Tuning (PEFT) adapters with an orthogonal pair decomposition, hyperspherical regularisation, and (in the GSD-LoRA variant) a set-level coherence objective. (3) Under LoRA, this regularisation gives a more stable optimisation profile: GSD-LoRA's post-peak validation degradation is 4.2×4.2\times shallower than plain LoRA at the same parameter footprint, and the time-averaged validation AUC across training is 1.82 pp higher. On the 17 datasets, GSD-LoRA matches or exceeds every re-evaluated baseline (92.82% vs. 91.58% for the strongest; paired Wilcoxon signed-rank p=0.015p=0.015, 13/17 per-dataset wins), with the largest gains on modern reenactment-heavy benchmarks (DSv1.1, DSv2). Under strict parameter budgets, LayerNorm-only tuning (≈\approx0.03% of the backbone) is the most stable configuration and matches the strongest baseline with a mean of 91.97%.

Figures & tables

Appendix figures & tables22 assets

Supplementary material from the paper’s appendix.

Appendix

Explore similar work

CardsList
  1. Honest Fusion Evaluation for Cross-Domain Deepfake Detection: Leakage Audits and Tail Robustness

    Nov 11, 2026Luke Collins, Chang-Tsun Li, Duc Thanh Nguyenscore fusionDeepfake Detection

  2. What Makes Adversarial Examples Transfer Across Deepfake Detectors?

    Sep 9, 2026Rafael M. Mamede, Pedro C. Neto, Ana F. SequeiraAdversarial RobustnessDeepfake Detection