克隆语音，真实后果：评估巴西选举诚信相关的政治深度伪造检测中的偏差

中文摘要 AI 辅助

生成式人工智能的最新进展使得在选举期间伪造言论和放大政治虚假信息变得更加容易。我们推出ParlaSpoof-BR，这是一个源自巴西众议院录音的音频深度伪造数据集，通过来自各种文本转语音和语音转换模型的合成话语进行扩展。使用ParlaSpoof-BR，我们对最先进的音频深度伪造检测器进行基准测试，检查它们对巴西葡萄牙语政治语音的泛化能力，并调查其预测中潜在的偏差。我们的分析表明，当前系统难以在数据集所代表的多样性中提供一致的决策，其中方法学因素（合成模型选择、操纵程度）比人口统计差异更占主导地位。ParlaSpoof-BR为在具有社会重要性且代表性不足的环境中研究音频深度伪造检测提供了特定领域的基准，支持开发更强大的巴西选举诚信检测系统。

英文摘要

Recent advances in generative artificial intelligence have made it easier to fabricate statements and amplify political disinformation during elections. We introduce ParlaSpoof-BR, an audio deepfake dataset derived from recordings of the Brazilian Chamber of Deputies and expanded with synthetic utterances from diverse text-to-speech and voice conversion models. Using ParlaSpoof-BR, we benchmark state-of-the-art audio deepfake detectors, examine their ability to generalize to Brazilian Portuguese political speech, and investigate potential biases in their predictions. Our analysis reveals that current systems struggle to provide consistent decisions across the diversity represented in the dataset, with methodological factors (synthesis model choice, manipulation extent) dominating over demographic disparities. ParlaSpoof-BR provides a domain-specific benchmark for studying audio deepfake detection in a socially consequential and underrepresented setting, supporting the development of more robust detection systems for electoral integrity in Brazil.

发表机构

• Federal University of Goiás（戈亚斯联邦大学）
• Ermis
• Federal University of Technology – Paraná（巴拉那联邦科技大学）

机构由 AI 辅助整理，请以论文原文为准。