defense arXiv Sep 4, 2025 · Sep 2025
Huhong Xian, Rui Liu, Berrak Sisman et al. · Inner Mongolia University · Johns Hopkins University +1 more
Detects frame-level synthetic speech segments in partial audio deepfakes using named entity recognition and attention aggregation
Output Integrity Attack audio
Different from traditional sentence-level audio deepfake detection (ADD), partial audio deepfake detection (PADD) requires frame-level positioning of the location of fake speech. While some progress has been made in this area, leveraging semantic information from audio, especially named entities, remains an underexplored aspect. To this end, we propose NE-PADD, a novel method for Partial Audio Deepfake Detection (PADD) that leverages named entity knowledge through two parallel branches: Speech Name Entity Recognition (SpeechNER) and PADD. The approach incorporates two attention aggregation mechanisms: Attention Fusion (AF) for combining attention weights and Attention Transfer (AT) for guiding PADD with named entity semantics using an auxiliary loss. Built on the PartialSpoof-NER dataset, experiments show our method outperforms existing baselines, proving the effectiveness of integrating named entity knowledge in PADD. The code is available at https://github.com/AI-S2-Lab/NE-PADD.
transformer Inner Mongolia University · Johns Hopkins University · The Chinese University of Hong Kong
ML Security Papers