# Open-Set Source Tracing as Compositional Factors via Structured Prototypes

arXiv: https://arxiv.org/abs/2607.03134 · HTML: https://mlsanity.com/paper/2607.03134/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 20 of its 28 references that are in the map.
- First posted on arXiv 3 Jul 2026.

## Builds on (most cited first, 20 of 20)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [VICReg: Variance-Invariance-Covariance Regularization for Self-Supervised Learning](https://mlsanity.com/paper/2105.04906/) (2021)
- [MLS: A Large-Scale Multilingual Dataset for Speech Research](https://mlsanity.com/paper/2012.03411/) (2020)
- [ASVspoof 2019: Future Horizons in Spoofed and Fake Audio Detection](https://mlsanity.com/paper/1904.05441/) (2019)
- [ASVspoof 2021: Towards Spoofed and Deepfake Speech Detection in the Wild](https://mlsanity.com/paper/2210.02437/) (2022)
- [ADD 2022: the First Audio Deep Synthesis Detection Challenge](https://mlsanity.com/paper/2202.08433/) (2022)
- [ASVspoof 5: Crowdsourced Speech Data, Deepfakes, and Adversarial Attacks at Scale](https://mlsanity.com/paper/2408.08739/) (2024)
- [ADD 2023: the Second Audio Deepfake Detection Challenge](https://mlsanity.com/paper/2305.13774/) (2023)
- [MLAAD: The Multi-Language Audio Anti-Spoofing Dataset](https://mlsanity.com/paper/2401.09512/) (2024)
- [Ring loss: Convex Feature Normalization for Face Recognition](https://mlsanity.com/paper/1803.00130/) (2018)
- [Source Tracing of Audio Deepfake Systems](https://mlsanity.com/paper/2407.08016/) (2024)
- [Codec-Based Deepfake Source Tracing via Neural Audio Codec Taxonomy](https://mlsanity.com/paper/2505.12994/) (2025)
- [STOPA: A Database of Systematic VariaTion Of DeePfake Audio for Open-Set Source Tracing and Attribution](https://mlsanity.com/paper/2505.19644/) (2025)
- [Source Verification for Speech Deepfakes](https://mlsanity.com/paper/2505.14188/) (2025)
- [Unveiling Audio Deepfake Origins: A Deep Metric learning And Conformer Network Approach With Ensemble Fusion](https://mlsanity.com/paper/2506.02085/) (2025)
- [Assessing the Impact of Speaker Identity in Speech Spoofing Detection](https://mlsanity.com/paper/2602.20805/) (2026)
- [Synthetic Speech Source Tracing using Metric Learning](https://mlsanity.com/paper/2506.02590/) (2025)
- [Open-Set Source Tracing of Audio Deepfake Systems](https://mlsanity.com/paper/2507.06470/) (2025)
- [Predefined Prototypes for Intra-Class Separation and Disentanglement](https://mlsanity.com/paper/2406.16145/) (2024)
- [Advancing Zero-Shot Open-Set Speech Deepfake Source Tracing](https://mlsanity.com/paper/2509.24674/) (2025)

## Built on by (most cited first, 1 of 1)

- [Clean Accuracy Does Not Guarantee Provenance Robustness: A Prospective Codec-Stress Evaluation of Audio Attribution](https://mlsanity.com/paper/2609.07981/) (2026)

## Abstract (arXiv)

Recent research expands beyond binary anti-spoofing with the emergence of Source Tracing, the task of identifying the specific generative origins of synthetic speech. However, current research often equates a "source" with its generative architecture. We propose redefining a source as a compositional tuple of Architecture, Training Data, and other training factors affecting the generated speech. We propose a framework using Structured Orthonormal Prototypes to minimize class overlap and intra-class variance. Our Subspace Partitioning strategy splits the embedding into architecture and data subspaces, while a residual subspace captures stochastic variability, enabling "compositional generalization" for novel factor combinations. This approach improves performance for partially seen sources and maintains robustness in fully open-set scenarios. MLAAD evaluations for Few-Shot open-set Identification show our approach significantly outperforms angular-margin baselines.