Machine learning makes multimedia data (e.g., images) more attractive, however, multimedia data is usually distributed and privacy sensitive. Multiple distributed multimedia clients can resort to federated learning (FL) to jointly learn a global shared model without requiring to share their private samples with any third-party entities. In this paper, we show that FL suffers from the cross-client generative adversarial networks (GANs)-based (C-GANs) attack, in which a malicious client (i.e., adversary) can reconstruct samples with the same distribution as the training samples from other clients (i.e., victims). Since a benign client's data can be leaked to the adversary, this attack brings the risk of local data leakage for clients in many security-critical FL applications. Thus, we propose Fed-EDKD (i.e., Federated Ensemble Data-free Knowledge Distillation) technique to improve the current popular FL schemes to resist C-GANs attack. In Fed-EDKD, each client submits a local model to the server for obtaining an ensemble global model. Then, to avoid model expansion, Fed-EDKD adopts data-free knowledge distillation techniques to transfer knowledge from the ensemble global model to a compressed model. By this way, Fed-EDKD reduces the adversary's control capability over the global model, so Fed-EDKD can effectively mitigate C-GANs attack. Finally, the experimental results demonstrate that Fed-EDKD significantly mitigates C-GANs attack while only incurring a slight accuracy degradation of FL.

翻译：机器学习使多媒体数据（如图像）更具吸引力，然而，多媒体数据通常呈分布式分布且涉及隐私敏感问题。多个分布式多媒体客户端可以借助联邦学习（FL）在不与任何第三方共享私有样本的情况下，共同学习一个全局共享模型。在本文中，我们展示了FL容易遭受基于跨客户端生成对抗网络（C-GANs）的攻击，这种攻击中，恶意客户端（即对手）能够重构与其他客户端（即受害者）训练样本具有相同分布的样本。由于良性客户端的数据可能泄露给对手，这种攻击在许多安全关键的FL应用中给客户端带来了本地数据泄露的风险。因此，我们提出了Fed-EDKD（即联邦集成无数据知识蒸馏）技术，以改进当前流行的FL方案，抵抗C-GANs攻击。在Fed-EDKD中，每个客户端向服务器提交本地模型，以获取集成全局模型。然后，为避免模型扩展，Fed-EDKD采用无数据知识蒸馏技术，将知识从集成全局模型迁移到压缩模型。通过这种方式，Fed-EDKD降低了对手对全局模型的控制能力，因此可以有效缓解C-GANs攻击。最后，实验结果表明，Fed-EDKD显著减轻了C-GANs攻击，同时仅导致FL的轻微精度下降。