[2604.01330] Evolutionary Multi-Objective Fusion of Deepfake Speech Detectors

Computer Science > Sound arXiv:2604.01330 (cs) [Submitted on 1 Apr 2026] Title:Evolutionary Multi-Objective Fusion of Deepfake Speech Detectors Authors:Vojtěch Staněk, Martin Perešíni, Lukáš Sekanina, Anton Firc, Kamil Malinka View a PDF of the paper titled Evolutionary Multi-Objective Fusion of Deepfake Speech Detectors, by Vojt\v{e}ch Stan\v{e}k and Martin Pere\v{s}\'ini and Luk\'a\v{s} Sekanina and Anton Firc and Kamil Malinka View PDF HTML (experimental) Abstract: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 ...