Evolutionary Multi-Objective Fusion of Deepfake Speech Detectors

Computer Science > Sound [Submitted on 1 Apr 2026] Evolutionary Multi-Objective Fusion of Deepfake Speech Detectors Vojtěch Staněk, Martin Perešíni, Lukáš Sekanina, Anton Firc, Kamil Malinka 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. Comments: Accepted to WCCI CEC 2026 Subjects: Sound (cs.SD); Artificial Intelligence (cs.AI); Cryptography and Security (cs.CR); Machine Learning (cs.LG); Neural and Evolutionary Computing (cs.NE) Cite as: arXiv:2604.01330 [cs.SD]   (or arXiv:2604.01330v1 [cs.SD] for this version)   https://doi.org/10.48550/arXiv.2604.01330 Focus to learn more Submission history From: Vojtěch Staněk [view email] [v1] Wed, 1 Apr 2026 19:17:59 UTC (533 KB) Access Paper: HTML (experimental) view license Current browse context: cs.SD < prev   |   next > new | recent | 2026-04 Change to browse by: cs cs.AI cs.CR cs.LG cs.NE References & Citations NASA ADS Google Scholar Semantic Scholar Export BibTeX Citation Bookmark Bibliographic Tools Bibliographic and Citation Tools Bibliographic Explorer Toggle Bibliographic Explorer (What is the Explorer?) Connected Papers Toggle Connected Papers (What is Connected Papers?) Litmaps Toggle Litmaps (What is Litmaps?) scite.ai Toggle scite Smart Citations (What are Smart Citations?) Code, Data, Media Demos Related Papers About arXivLabs Which authors of this paper are endorsers? | Disable MathJax (What is MathJax?)