The rapid advancement of generative models has enabled the creation of increasingly stealthy synthetic voices, commonly referred to as audio deepfakes. A recent technique, FOICE [USENIX'24], demonstrates a particularly alarming capability: generating a victim's voice from a single facial image, without requiring any voice sample. By exploiting correlations between facial and vocal features, FOICE produces synthetic voices realistic enough to bypass industry-standard authentication systems, including WeChat Voiceprint and Microsoft Azure. This raises serious security concerns, as facial images are far easier for adversaries to obtain than voice samples, dramatically lowering the barrier to large-scale attacks. In this work, we investigate two core research questions: (RQ1) can state-of-the-art audio deepfake detectors reliably detect FOICE-generated speech under clean and noisy conditions, and (RQ2) whether fine-tuning these detectors on FOICE data improves detection without overfitting, thereby preserving robustness to unseen voice generators such as SpeechT5. Our study makes three contributions. First, we present the first systematic evaluation of FOICE detection, showing that leading detectors consistently fail under both standard and noisy conditions. Second, we introduce targeted fine-tuning strategies that capture FOICE-specific artifacts, yielding significant accuracy improvements. Third, we assess generalization after fine-tuning, revealing trade-offs between specialization to FOICE and robustness to unseen synthesis pipelines. These findings expose fundamental weaknesses in today's defenses and motivate new architectures and training protocols for next-generation audio deepfake detection.

翻译：生成模型的快速发展使得合成语音（通常称为音频深度伪造）的隐蔽性日益增强。近期技术FOICE [USENIX'24]展示了一种尤为令人警觉的能力：仅凭单张面部图像即可生成受害者语音，无需任何语音样本。通过利用面部特征与声学特征之间的相关性，FOICE生成的合成语音逼真到足以绕过行业标准认证系统（包括微信声纹识别和微软Azure），这引发了严重的安全担忧，因为攻击者获取面部图像远比获取语音样本容易，从而大幅降低了发起大规模攻击的门槛。本研究聚焦两个核心研究问题：（RQ1）在纯净与噪声条件下，现有最先进的音频深度伪造检测器能否可靠识别FOICE生成的语音；（RQ2）基于FOICE数据微调这些检测器能否在不导致过拟合的前提下提升检测性能，从而保持对未见语音生成器（如SpeechT5）的鲁棒性。本研究的贡献包括：首先，我们首次对FOICE检测进行了系统性评估，结果表明主流检测器在标准及噪声条件下均持续失效；其次，我们提出了针对FOICE特有伪影的定向微调策略，显著提升了检测准确率；最后，我们评估了微调后的泛化能力，揭示了针对FOICE的特化优化与对未见合成流程的鲁棒性之间的权衡。这些发现揭示了当前防御体系的基础性缺陷，并为新一代音频深度伪造检测的架构设计与训练协议提供了改进方向。