研究人员开发了新的工具和方法来对抗音频深度伪造。AUDDT是一个开源工具包，旨在评估深度伪造检测器在各种音频数据集和操纵类型上的泛化能力。FoeGlass提供了一种自动化的红队测试方法，通过生成对抗性音频样本，利用LLM来发现音频深度伪造检测器的盲点。此外，SARA是一个诊断框架，用于评估用于深度伪造检测的音频语言模型的推理和连贯性，即使在对抗性攻击下也是如此。 AI
影响 这些在检测和分析工具方面的进展对于提高AI生成音频对策的鲁棒性和可靠性至关重要。
排序理由 该集群包含多篇介绍音频深度伪造检测新框架和工具包的研究论文。
AI 生成摘要 · Google Gemini · 来自 4 个来源。 我们如何撰写摘要 →
arXiv:2509.21597v2 Announce Type: replace-cross Abstract: With the prevalence of artificial intelligence (AI)-generated content, such as audio deepfakes, a large body of recent work has focused on developing deepfake detection techniques. However, existing benchmarks employ a nar…
arXiv:2606.05101v1 Announce Type: cross Abstract: Audio deepfake detection (ADD) models are critical for countering the malicious use of text-to-speech (TTS) models. Evaluating and strengthening ADD models requires developing datasets that span the space of generated audio and hi…
Audio deepfake detection (ADD) models are critical for countering the malicious use of text-to-speech (TTS) models. Evaluating and strengthening ADD models requires developing datasets that span the space of generated audio and highlight high-error regions. Existing dataset devel…
arXiv:2601.03615v2 Announce Type: replace Abstract: Audio Language Models (ALMs) offer a promising shift towards explainable audio deepfake detections (ADD), moving beyond \textit{black-box} classifiers by providing transparency to their predictions via reasoning traces. However,…