FedComm: Federated Learning as a Medium for Covert Communication

TL;DR

This paper demonstrates that federated learning can be exploited as a covert channel for hidden communication, introducing FedComm, which enables stealthy data transfer with minimal impact on model training.

Contribution

The paper presents FedComm, a novel method for covert communication within federated learning, showing its effectiveness across various models and domains with theoretical and empirical validation.

Findings

FedComm achieves 100% payload delivery before convergence.

It operates independently of application domain and neural network architecture.

Provides a stealthy communication channel with minimal training disruption.

Abstract

Proposed as a solution to mitigate the privacy implications related to the adoption of deep learning, Federated Learning (FL) enables large numbers of participants to successfully train deep neural networks without having to reveal the actual private training data. To date, a substantial amount of research has investigated the security and privacy properties of FL, resulting in a plethora of innovative attack and defense strategies. This paper thoroughly investigates the communication capabilities of an FL scheme. In particular, we show that a party involved in the FL learning process can use FL as a covert communication medium to send an arbitrary message. We introduce FedComm, a novel multi-system covert-communication technique that enables robust sharing and transfer of targeted payloads within the FL framework. Our extensive theoretical and empirical evaluations show that FedComm provides a stealthy communication channel, with minimal disruptions to the training process. Our experiments show that FedComm successfully delivers 100% of a payload in the order of kilobits before the FL procedure converges. Our evaluation also shows that FedComm is independent of the application domain and the neural network architecture used by the underlying FL scheme.