PerDoor: Persistent Non-Uniform Backdoors in Federated Learning using Adversarial Perturbations

Understand

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.