🛰️ Daily AI Frontier
‹ back to 2026-07-30

Foundation Models for Face Presentation Attack Detection: A Unified Linear-Probing Benchmark

Research Face Anti-Spoofing

Ranking

Overall 59
Content 65
Popularity 44

Observed public metrics from 1 member.

Representative image for Foundation Models for Face Presentation Attack Detection: A Unified Linear-Probing Benchmark

Merged summary

TL;DR - A unified linear-probing benchmark of 24 frozen vision encoders finds that foundation models encode useful face presentation-attack signals, but their performance transfers inconsistently across datasets due to domain shift.

  • Frozen encoders paired with only a linear classifier achieved strong intra-dataset detection performance.
  • InternViT-6B had the lowest mean intra-dataset error.
  • CLIP ViT-B/32 offered the best cross-dataset transfer–compute trade-off among the evaluated probes.
  • Model scale helped within some families, but architecture and pretraining mattered more; explicit adaptation remains necessary for robust transfer.

Sources (1)

Foundation Models for Face Presentation Attack Detection: A Unified Linear-Probing Benchmark

arXiv cs.LG Peter Lorenz, Anjith George, SĂ©bastien Marcel 2026-07-29 arXiv:2607.26993
Public signals Semantic Scholar citations 0 · Semantic Scholar influential citations 0
Providers: Hugging Face · N/A OpenAlex · N/A Publisher · N/A Semantic Scholar · Citations 0 · Influential citations 0 X · N/A Fetched 2026-08-28 14:33:30.740742 UTC

TL;DR - A unified linear-probing benchmark of 24 frozen vision encoders finds that foundation models encode useful face presentation-attack signals, but their performance transfers inconsistently across datasets due to domain shift.

  • Frozen encoders paired with only a linear classifier achieved strong intra-dataset detection performance.
  • InternViT-6B had the lowest mean intra-dataset error.
  • CLIP ViT-B/32 offered the best cross-dataset transfer–compute trade-off among the evaluated probes.
  • Model scale helped within some families, but architecture and pretraining mattered more; explicit adaptation remains necessary for robust transfer.
item →