What Makes Adversarial Examples Transfer Across Deepfake Detectors?

arXiv:2609.10002 · cs.CV, cs.AI, cs.CR, cs.LG · Submitted 2026-09-09 · Read on arXiv

cs.CV, cs.AI, cs.CR, cs.LG

Submitted: 2026-09-09

Updated: 2026-10-09

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Terminology

• Adversarial Examples — 2× in this paper · explained in 2 episodes
• Adversarial Transferability — 1× in this paper · explained in 1 episode
• Attack Success Rate (ASR) — 1× in this paper · explained in 2 episodes
• Robustness — 1× in this paper · explained in 5 episodes
• Transferability — 1× in this paper · explained in 4 episodes

Sources

• The DeepFake Detection Challenge (DFDC) Dataset
• Deepfake detectors are DUMB: A benchmark to assess adversarial training robustness under transferability constraints

Related papers

• Loss Knows Best: Detecting Annotation Errors in Videos via Loss Trajectories
• AnchorWeave: World-Consistent Video Generation with Retrieved Local Spatial Memories
• Benchmarking the Robustness of Foundation Models for Mammography under Domain Shift
• MambaX-Net: Dual-Input Mamba-Enhanced Cross-Attention Network for Longitudinal MRI Segmentation
• TeleOCR: Navigating Document Parsing Across Digital and Camera-Captured Documents
• A Survey on Efficient Vision-Language-Action Models