SOURCE-LINKED INTELLIGENCE

What Makes Adversarial Examples Transfer Across Deepfake Detectors?

arXiv · AI, language, vision and robotics · article · Sep 9, 2026 · UTC

Deepfake detectors remain vulnerable to transfer-based black-box attacks, in which adversarial examples are generated on a source surrogate model and transferred to a target model, unknown to the attacker. Yet how source--target compatibility shapes attack success remains poorly understood. Prior studies evaluate limited detector pools and rarely disentangle architectural from training factors. We conduct a controlled evaluation of adversarial transferability across 60 detectors spanning six backbones, two pretraining regimes, and five training-data configurations, using two attack procedures:

Read original source ↗ Open in workspace

recordType

paper

region

Global