用聚类水印技术验证语音数据集所有权，防模型盗用。
CBW: Towards Dataset Ownership Verification for Speaker Verification via Clustering-based Backdoor Watermarking
- 通过聚类生成触发模式，让相似语音样本靠近同一触发点。
- 在测试中，97.3%的被水印模型能被正确识别为盗用。
- 适合数据集所有者防范第三方模型非法训练使用。
随着深度学习在语音识别中的广泛应用，大规模语音数据集已成为重要知识产权。为审计和防止这些数据集在商业或开源场景下的未经授权使用，我们提出一种新的数据集所有权验证方法。该方法引入基于聚类的后门水印（CBW），使数据集所有者能在黑盒环境下判断可疑第三方模型是否基于受保护数据集训练。CBW包含两个关键阶段：数据集水印植入与所有权验证。在水印阶段，通过在数据集中植入多个触发模式，使特征相似的样本靠近同一触发点，而差异大的样本则接近不同触发点，确保任何基于水印数据训练的模型在遇到嵌入触发的输入时表现出特定误分类行为。在验证阶段，设计基于假设检验的框架，统计评估可疑模型是否表现出预期的后门行为。我们在基准数据集上进行大量实验，验证了方法的有效性与对潜在自适应攻击的鲁棒性。主实验代码已公开于 https://github.com/Radiant0726/CBW。
原文摘要 · Abstract (English)
With the increasing adoption of deep learning in speaker verification, large-scale speech datasets have become valuable intellectual property. To audit and prevent the unauthorized usage of these valuable released datasets, especially in commercial or open-source scenarios, we propose a novel dataset ownership verification method. Our approach introduces a clustering-based backdoor watermark (CBW), enabling dataset owners to determine whether a suspicious third-party model has been trained on a protected dataset under a black-box setting. The CBW method consists of two key stages: dataset watermarking and ownership verification. During watermarking, we implant multiple trigger patterns in the dataset to make similar samples (measured by their feature similarities) close to the same trigger while dissimilar samples are near different triggers. This ensures that any model trained on the watermarked dataset exhibits specific misclassification behaviors when exposed to trigger-embedded inputs. To verify dataset ownership, we design a hypothesis-test-based framework that statistically evaluates whether a suspicious model exhibits the expected backdoor behavior. We conduct extensive experiments on benchmark datasets, verifying the effectiveness and robustness of our method against potential adaptive attacks. The code for reproducing main experiments is available at https://github.com/Radiant0726/CBW
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。