paper-with-me

Papers

A Data-Driven Diffusion-based Approach for Audio Deepfake Explanations

2025-06-03 · Petr Grinberg, Ankur Kumar, Surya Koppisetti, Gaurav Bharaj

Evaluating explainability techniques, such as SHAP and LRP, in the context of audio deepfake detection is challenging due to lack of clear ground truth annotations. In the cases when we are able to obtain the ground truth, we find that these methods struggle to provide accurate explanations. In this work, we propose a novel data-driven approach to identify artifact regions in deepfake audio. We consider paired real and vocoded audio, and use the difference in time-frequency representation as the ground-truth explanation. The difference signal then serves as a supervision to train a diffusion model to expose the deepfake artifacts in a given vocoded audio. Experimental results on the VocV4 and LibriSeVoc datasets demonstrate that our method outperforms traditional explainability techniques, both qualitatively and quantitatively.

📄 PDF Abstract BibTeX arXiv:2506.03425

Code (0)

등록된 구현이 없습니다.

Tasks

Audio Deepfake DetectionDeepFake DetectionFace Swapping

Methods 이 논문이 사용한 방법론

SHAP 설명 없음
Diffusion Diffusion models generate samples by gradually removing noise from a signal, and their training objective can be expressed as a reweighted variational lower-bound…

Similar Papers 제목 키워드 기반

Do You Really Mean That? Content Driven Audio-Visual Deepfake Dataset and Multimodal Method for Temporal Forgery Localization

2022-04-13 · Zhixi Cai, Kalin Stefanov, Abhinav Dhall, Munawar Hayat

Due to its high societal impact, deepfake detection is getting active attention in the computer vision community. Most deepfake detection methods rely on identity, facial attributes, and adversarial perturbation-based sp…

BenchmarkingDeepFake DetectionTemporal Forgery Localization

AV-Deepfake1M: A Large-Scale LLM-Driven Audio-Visual Deepfake Dataset

2023-11-26 · Zhixi Cai, Shreya Ghosh, Aman Pankaj Adatia, Munawar Hayat 외

The detection and localization of highly realistic deepfake audio-visual content are challenging even for the most advanced state-of-the-art methods. While most of the research efforts in this domain are focused on detec…

DeepFake DetectionFace SwappingTemporal Forgery Localization

Toward Robust Real-World Audio Deepfake Detection: Closing the Explainability Gap

2024-10-09 · Georgia Channing, Juil Sock, Ronald Clark, Philip Torr 외

The rapid proliferation of AI-manipulated or generated audio deepfakes poses serious challenges to media integrity and election security. Current AI-driven detection solutions lack explainability and underperform in real…

Audio Deepfake DetectionDeepFake DetectionFace Swapping

Omni-Fake: Benchmarking Unified Multimodal Social Media Deepfake Detection

2026-05-02 · Tianxiao Li, Zhenglin Huang, Haiquan Wen, Yiwei He 외 arxiv

Multimodal deepfakes are proliferating on social media and threaten authenticity, information integrity, and digital forensics. Existing benchmarks are constrained by their single-modality scope, simplified manipulations…

DeepFake Detection

The Tug-of-War Between Deepfake Generation and Detection

2024-07-08 · Hannah Lee, Changyeon Lee, Kevin Farhat, Lin Qiu 외

Multimodal generative models are rapidly evolving, leading to a surge in the generation of realistic video and audio that offers exciting possibilities but also serious risks. Deepfake videos, which can convincingly impe…

Face SwappingMisinformationVideo Generation