As industrial applications are increasingly automated by machine learning models, enforcing personal data ownership and intellectual property rights requires tracing training data back to their rightful owners. Membership inference algorithms approach this problem by using statistical techniques to discern whether a target sample was included in a model's training set. However, existing methods only utilize the unaltered target sample or simple augmentations of the target to compute statistics. Such a sparse sampling of the model's behavior carries little information, leading to poor inference capabilities. In this work, we use adversarial tools to directly optimize for queries that are discriminative and diverse. Our improvements achieve significantly more accurate membership inference than existing methods, especially in offline scenarios and in the low false-positive regime which is critical in legal settings. Code is available at https://github.com/YuxinWenRick/canary-in-a-coalmine.
翻译:由于工业应用日益通过机器学习模式实现自动化,执行个人数据所有权和知识产权要求将培训数据追溯到其合法拥有者手中。成员推算算算法通过使用统计技术来解决这一问题,以辨别是否将目标样本纳入模型培训集;然而,现有方法仅使用未改变的目标抽样或指标的简单增强来计算统计数据。这种对模型行为的稀疏抽样几乎没有信息,导致推断能力差。在这项工作中,我们使用对抗工具直接优化具有歧视性和多样性的查询。我们的改进比现有方法,特别是在离线情景和在法律环境中至关重要的低伪阳性制度中,取得了比现有方法更准确的归属推断。守则可在https://github.com/YuxinWenRick/canary-in-a-coalmine查阅。