Federated Learning (FL) enables numerous participants to train deep learning models collaboratively without exposing their personal, potentially sensitive data, making it a promising solution for data privacy in collaborative training. The distributed nature of FL and unvetted data, however, makes it inherently vulnerable to backdoor attacks: In this scenario, an adversary injects backdoor functionality into the centralized model during training, which can be triggered to cause the desired misclassification for a specific adversary-chosen input. A range of prior work establishes successful backdoor injection in an FL system; however, these backdoors are not demonstrated to be long-lasting. The backdoor functionality does not remain in the system if the adversary is removed from the training process since the centralized model parameters continuously mutate during successive FL training rounds. Therefore, in this work, we propose PerDoor, a persistent-by-construction backdoor injection technique for FL, driven by adversarial perturbation and targeting parameters of the centralized model that deviate less in successive FL rounds and contribute the least to the main task accuracy. An exhaustive evaluation considering an image classification scenario portrays on average $10.5\times$ persistence over multiple FL rounds compared to traditional backdoor attacks. Through experiments, we further exhibit the potency of PerDoor in the presence of state-of-the-art backdoor prevention techniques in an FL system. Additionally, the operation of adversarial perturbation also assists PerDoor in developing non-uniform trigger patterns for backdoor inputs compared to uniform triggers (with fixed patterns and locations) of existing backdoor techniques, which are prone to be easily mitigated.
翻译:联邦学习组织(FL)使许多参与者能够合作培训深层次学习模式,而不会暴露其个人和潜在敏感数据,从而使其成为合作培训中数据隐私的一个有希望的解决办法。但是,FL和未审数据分布式的性质使得它天生容易受到幕后攻击:在这一情景中,对手在培训期间将后门功能注入中央模式,这可能会引发对特定对手选择输入的输入造成预期的错误分类。先前的一系列工作在FL系统中确立了成功的后门注射;然而,这些后门并不证明是长期的。如果在FL连续的培训回合中集中模式参数不断变异,将对手从培训过程中移除,后门功能就不会留在系统中。因此,在这项工作中,我们建议PerDoor为FL提供一种持续的逐道后门注射技术,这种技术在FL连续的回合中偏差较少,并且容易导致主要任务的准确性。 全面评价设想一个图像分类假设方案,在平均的10.5\时间将对手从培训过程中清除前的触发,在FL的后端试验中,我们通过常规的固定的周期,在FL轮中进行长期的周期内进行。