Pith. sign in

REVIEW 4 cited by

Source Tracing of Audio Deepfake Systems

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2407.08016 v1 pith:EMDR3C2Z submitted 2024-07-10 eess.AS cs.SD

classification eess.AScs.SD
keywords audiogenerationdeepfakesystemsystemsanti-spoofingattributesdeepfakes
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Recent progress in generative AI technology has made audio deepfakes remarkably more realistic. While current research on anti-spoofing systems primarily focuses on assessing whether a given audio sample is fake or genuine, there has been limited attention on discerning the specific techniques to create the audio deepfakes. Algorithms commonly used in audio deepfake generation, like text-to-speech (TTS) and voice conversion (VC), undergo distinct stages including input processing, acoustic modeling, and waveform generation. In this work, we introduce a system designed to classify various spoofing attributes, capturing the distinctive features of individual modules throughout the entire generation pipeline. We evaluate our system on two datasets: the ASVspoof 2019 Logical Access and the Multi-Language Audio Anti-Spoofing Dataset (MLAAD). Results from both experiments demonstrate the robustness of the system to identify the different spoofing attributes of deepfake generation systems.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 4 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. Neural Codec Source Tracing: Toward Comprehensive Attribution in Open-Set Condition

    cs.SD 2025-01 conditional novelty 6.0 of 10

    A new open-set neural codec source tracing benchmark and dataset shows strong in-distribution classification and OOD detection, but poor generalization to unseen real audio.

  2. Towards Explainable Spoofed Speech Attribution and Detection:a Probabilistic Approach for Characterizing Speech Synthesizer Components

    eess.AS 2025-02 conditional novelty 5.0 of 10

    Probabilistic attribute embeddings derived from countermeasure embeddings match raw embedding performance on spoofed speech detection and attack attribution while providing component-level explanations.

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

    eess.AS 2024-12 conditional novelty 5.0 of 10

    x-vector embeddings and a Rényi divergence fusion loss achieve the best audio deepfake source attribution on ASVspoof 2019 and CFAD, though the benchmark protocol is non-standard.

  4. Unmasking Synthetic Realities in Generative AI: A Comprehensive Review of Adversarially Robust Deepfake Detection Systems

    cs.CR 2025-07 conditional novelty 3.0 of 10

    A systematic review of deepfake detection finds a pervasive lack of adversarial robustness evaluation across all modalities and calls for resilient, modality-agnostic detectors.

Pith tools