发表机构
The Hong Kong Polytechnic University; Communication University of China; Beijing Institute of Technology（香港理工大学; 中国传媒大学; 北京理工大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
针对持续音频深度伪造检测，提出RAMI协议和RF-Prompt方法，通过共享真实提示与继承伪造专家结合软融合，在受控实验中取得最优EER。
AI 中文摘要
持续音频深度伪造检测要求在学习新出现的深度伪造方法的同时，保持对先前遇到语音的判别能力。现有的数据集增量评估同时改变了真实语音域和深度伪造机制，使得难以区分它们的影响。我们在相同的训练、开发和评估池上构建了五个任务组织，以在受控样本预算下研究这些因素。我们提出的真实锚定机制增量（RAMI）协议反映了实际场景，其中可用的真实语音提供了重复出现的混合域参考，而新的深度伪造机制则增量到达。我们进一步提出了RF-Prompt，一种不对称的持续提示学习方法，通过共享的真实提示保留可复用的真实语音知识，并通过具有正交残差的继承伪造专家扩展机制特定知识。输入自适应软融合将累积的专家组合成固定数量的注入令牌，而无需在推理时提供任务身份。在RAMI上，RF-Prompt实现了10.110%的平均EER和10.370%的合并EER，优于所有评估的持续学习基线。在五个受控协议中，RAMI产生了最低的常见平均和合并EER。组件消融、有限数据实验和跨骨干评估进一步验证了所提出的设计。
英文摘要
Continual audio deepfake detection requires learning newly emerging deepfake methods while retaining discrimination of previously encountered speech. Existing dataset-incremental evaluation changes both real-speech domains and deepfake mechanisms, making their effects difficult to distinguish. We construct five task organizations over identical training, development, and evaluation pools to study these factors under a controlled sample budget. Our proposed Real-Anchored Mechanism-Incremental (RAMI) protocol reflects the practical setting in which available real speech provides a recurring mixed-domain reference while new deepfake mechanisms arrive incrementally. We further propose RF-Prompt, an asymmetric continual prompt-learning method that preserves reusable real-speech knowledge through a shared real prompt and expands mechanism-specific knowledge through inherited fake experts with orthogonal residuals. Input-adaptive soft fusion combines the accumulated experts into a fixed number of injected tokens without requiring task identity at inference. On RAMI, RF-Prompt achieves 10.110% average EER and 10.370% pooled EER, outperforming all evaluated continual-learning baselines. Across the five controlled protocols, RAMI yields the lowest common-average and pooled EER. Component ablations, limited-data experiments, and cross-backbone evaluations further validate the proposed design.
