paper-with-me

Papers

Towards Reliable Audio Deepfake Attribution and Model Recognition: A Multi-Level Autoencoder-Based Framework

2025-08-04 · Andrea Di Pierno, Luca Guarnera, Dario Allegra, Sebastiano Battiato arxiv

The proliferation of audio deepfakes poses a growing threat to trust in digital communications. While detection methods have advanced, attributing audio deepfakes to their source models remains an underexplored yet crucial challenge. In this paper we introduce LAVA (Layered Architecture for Voice Attribution), a hierarchical framework for audio deepfake detection and model recognition that leverages attention-enhanced latent representations extracted by a convolutional autoencoder trained solely on fake audio. Two specialized classifiers operate on these features: Audio Deepfake Attribution (ADA), which identifies the generation technology, and Audio Deepfake Model Recognition (ADMR), which recognize the specific generative model instance. To improve robustness under open-set conditions, we incorporate confidence-based rejection thresholds. Experiments on ASVspoof2021, FakeOrReal, and CodecFake show strong performance: the ADA classifier achieves F1-scores over 95% across all datasets, and the ADMR module reaches 96.31% macro F1 across six classes. Additional tests on unseen attacks from ASVpoof2019 LA and error propagation analysis confirm LAVA's robustness and reliability. The framework advances the field by introducing a supervised approach to deepfake attribution and model recognition under open-set conditions, validated on public benchmarks and accompanied by publicly released models and code. Models and code are available at https://www.github.com/adipiz99/lava-framework.

📄 PDF Abstract BibTeX arXiv:2508.02521

Code (0)

등록된 구현이 없습니다.

Tasks

Audio Deepfake Detection

Similar Papers 제목 키워드 기반

Audio Deepfake Attribution: An Initial Dataset and Investigation

2022-08-21 · Xinrui Yan, Jiangyan Yi, JianHua Tao, Jie Chen

The rapid progress of deep speech synthesis models has posed significant threats to society such as malicious manipulation of content. This has led to an increase in studies aimed at detecting so-called deepfake audio. H…

Audio GenerationBinary ClassificationFace SwappingSpeech Synthesis

Generalized Source Tracing: Detecting Novel Audio Deepfake Algorithm with Real Emphasis and Fake Dispersion Strategy

2024-06-05 · Yuankun Xie, Ruibo Fu, Zhengqi Wen, Zhiyong Wang 외

With the proliferation of deepfake audio, there is an urgent need to investigate their attribution. Current source tracing methods can effectively distinguish in-distribution (ID) categories. However, the rapid evolution…

Audio Deepfake DetectionDeepFake DetectionFace Swapping

Attribution-Guided Multimodal Deepfake Detection via Cross-Modal Forensic Fingerprints

2026-04-29 · Wasim Ahmad, Wei Zhang, Xuerui Mao arxiv

Audio-visual deepfakes have reached a level of realism that makes perceptual detection unreliable, threatening media integrity and biometric security. While multimodal detection has shown promise, most approaches are bin…

Binary ClassificationDeepFake Detection

Investigating Prosodic Signatures via Speech Pre-Trained Models for Audio Deepfake Source Attribution

2024-12-23 · Orchid Chetia Phukan, Drishti Singh, Swarup Ranjan Behera, Arun Balaji Buduru 외

In this work, we investigate various state-of-the-art (SOTA) speech pre-trained models (PTMs) for their capability to capture prosodic signatures of the generative sources for audio deepfake source attribution (ADSD). Th…

Audio Deepfake DetectionDeepFake DetectionFace SwappingSpeaker Recognition+2

Beyond Seeing Is Believing: On Crowdsourced Detection of Audiovisual Deepfakes

2026-05-06 · Michael Soprano, Andrea Cioci, Stefano Mizzaro arxiv

Deepfakes are increasingly realistic and easy to produce, raising concerns about the reliability of human judgments in misinformation settings. We study audiovisual deepfake detection by measuring how consistently crowd …

DeepFake Detection