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
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.
Forward citations
Cited by 4 Pith papers
-
Neural Codec Source Tracing: Toward Comprehensive Attribution in Open-Set Condition
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.
-
Towards Explainable Spoofed Speech Attribution and Detection:a Probabilistic Approach for Characterizing Speech Synthesizer Components
Probabilistic attribute embeddings derived from countermeasure embeddings match raw embedding performance on spoofed speech detection and attack attribution while providing component-level explanations.
-
Investigating Prosodic Signatures via Speech Pre-Trained Models for Audio Deepfake Source Attribution
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.
-
Unmasking Synthetic Realities in Generative AI: A Comprehensive Review of Adversarially Robust Deepfake Detection Systems
A systematic review of deepfake detection finds a pervasive lack of adversarial robustness evaluation across all modalities and calls for resilient, modality-agnostic detectors.
Discussion (0). Continue with ORCID to comment.