SOURCE-LINKED INTELLIGENCE

Comparing Self-Supervised and Domain-Invariant Features for Cross-Domain Voice Phishing Detection

arXiv · AI, language, vision and robotics · article · Sep 7, 2026 · UTC

Voice phishing detection faces three critical challenges: real criminal recordings are unavailable due to privacy constraints; when available, only a handful of samples exist, insufficient for fine-tuning; and lightweight acoustic-only detection is needed as an alternative to large self-supervised models. We compare domain-invariant prosodic features and self-supervised representations (HuBERT, wav2vec2.0) through cross-domain evaluation-training on scenario-based actor recordings and testing on authentic criminal calls. Domain-invariant prosodic features achieve 69.5% F1 zero-shot and 71.0% w

Read original source ↗ Open in workspace

recordType

paper

region

Global