Covert Communication Based on the Poisoning Attack in Federated Learning

TL;DR

This paper introduces a novel covert communication method in federated learning using poisoning attacks, achieving perfect message transmission and exposing vulnerabilities in current defenses.

Contribution

The paper presents a new poisoning attack-based covert communication technique specifically designed for federated learning, demonstrating its effectiveness and highlighting security challenges.

Findings

Achieves 100% accuracy in covert message transmission

Proves to be stealthy and robust against existing defenses

Identifies limitations of current defense methods

Abstract

Covert communication has become an important area of research in computer security. It involves hiding specific information on a carrier for message transmission and is often used to transmit private data, military secrets, and even malware. In deep learning, many methods have been developed for hiding information in models to achieve covert communication. However, these methods are not applicable to federated learning, where model aggregation invalidates the exact information embedded in the model by the client. To address this problem, we propose a novel method for covert communication in federated learning based on the poisoning attack. Our approach achieves 100% accuracy in covert message transmission between two clients and is shown to be both stealthy and robust through extensive experiments. However, existing defense methods are limited in their effectiveness against our attack scheme, highlighting the urgent need for new protection methods to be developed. Our study emphasizes the necessity of research in covert communication and serves as a foundation for future research in federated learning attacks and defenses.