Federated learning algorithms are developed both for efficiency reasons and to ensure the privacy and confidentiality of personal and business data, respectively. Despite no data being shared explicitly, recent studies showed that the mechanism could still leak sensitive information. Hence, secure aggregation is utilized in many real-world scenarios to prevent attribution to specific participants. In this paper, we focus on the quality of individual training datasets and show that such quality information could be inferred and attributed to specific participants even when secure aggregation is applied. Specifically, through a series of image recognition experiments, we infer the relative quality ordering of participants. Moreover, we apply the inferred quality information to detect misbehaviours, to stabilize training performance, and to measure the individual contributions of participants.
翻译:联邦学习算法的制定既是为了提高效率,也是为了确保个人和商业数据的隐私和保密性。尽管没有明确分享数据,但最近的研究表明,这一机制仍然可能泄露敏感信息。因此,在许多现实世界情景中,安全汇总被利用,以防止归属于特定参与者。在本文件中,我们侧重于个人培训数据集的质量,并表明即使在应用安全汇总时,这种质量信息也可以推断给特定参与者。具体地说,通过一系列图像识别实验,我们推断参与者的相对质量顺序。此外,我们运用推断的质量信息来发现错误行为,稳定培训业绩,衡量参与者的个人贡献。