Manipulated Regions Localization For Partially Deepfake Audio: A Survey

2025-06-17

AI Summary

To address the challenge of detecting deepfake audio with localized, stealthy manipulations—posing significant security risks—this paper presents the first systematic survey of tampered region localization. We formally define the task, delineate its technical boundaries, and identify key evaluation bottlenecks. A unified survey framework is proposed, integrating spectral analysis, temporal modeling, self-supervised localization, and explainable AI approaches, while comparatively analyzing detector-driven versus segmentation-based localization paradigms. We construct the first multi-dimensional technical taxonomy, clarifying performance limitations of state-of-the-art methods in cross-model robustness, fine-grained localization accuracy, and real-world adaptability. This work fills a critical gap in the literature by providing the first comprehensive, structured review of tampered region localization for deepfake audio, establishing foundational theoretical insights and a principled technical roadmap for future research.

Technology Category

• Natural Language Processing: Fact-Checking / Misinformation Detection (NLP Focus)
• Intelligent Robots: Localization, Mapping, and Navigation
• Search and Optimization: Local Search

Application Category

• Security and Privacy: Large-scale security measurements
• User Modeling, Personalization and Recommendation: Attacks and countermeasures in recommendation systems
• Web Mining and Content Analysis: Robustness and generalizability of Web mining methods

Abstract

With the development of audio deepfake techniques, attacks with partially deepfake audio are beginning to rise. Compared to fully deepfake, it is much harder to be identified by the detector due to the partially cryptic manipulation, resulting in higher security risks. Although some studies have been launched, there is no comprehensive review to systematically introduce the current situations and development trends for addressing this issue. Thus, in this survey, we are the first to outline a systematic introduction for partially deepfake audio manipulated region localization tasks, including the fundamentals, branches of existing methods, current limitations and potential trends, providing a revealing insight into this scope.

Problem

• Locate manipulated regions in partially deepfake audio
• Survey existing methods for deepfake audio detection
• Analyze limitations and trends in audio manipulation localization

Innovation

• Survey on partially deepfake audio localization
• Systematic review of detection methods
• Analysis of current limitations and trends