Evolutionary Multi-Objective Fusion of Deepfake Speech Detectors
This addresses the need for more efficient deepfake speech detectors, offering a trade-off between accuracy and computational cost, though it is incremental as it builds on existing SSL-based detectors.
The paper tackles the problem of oversized deepfake speech detection systems by proposing an evolutionary multi-objective fusion framework that minimizes detection error and complexity, achieving 2.37% EER and reducing parameters by half compared to standard methods.
While deepfake speech detectors built on large self-supervised learning (SSL) models achieve high accuracy, employing standard ensemble fusion to further enhance robustness often results in oversized systems with diminishing returns. To address this, we propose an evolutionary multi-objective score fusion framework that jointly minimizes detection error and system complexity. We explore two encodings optimized by NSGA-II: binary-coded detector selection for score averaging and a real-valued scheme that optimizes detector weights for a weighted sum. Experiments on the ASVspoof 5 dataset with 36 SSL-based detectors show that the obtained Pareto fronts outperform simple averaging and logistic regression baselines. The real-valued variant achieves 2.37% EER (0.0684 minDCF) and identifies configurations that match state-of-the-art performance while significantly reducing system complexity, requiring only half the parameters. Our method also provides a diverse set of trade-off solutions, enabling deployment choices that balance accuracy and computational cost.