mlsanityData to 7 Oct 2026

Covert Communication Based on the Poisoning Attack in Federated Learning

arXiv 2306.01342 ↗First posted 2 Jun 2023cs.LG cs.CRcited by 0

Not on the map. Why?

Abstract (arXiv)

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.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 32 of its 53 references that are in the map. First posted on arXiv 2 Jun 2023.

Builds on

32 of 53 references.

References · 32

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2016Communication-Efficient Learning of Deep Networks from Decentralized Datacited by 7,592
  3. 2019Advances and Open Problems in Federated Learningcited by 3,021
  4. 2018How To Backdoor Federated Learningcited by 745
  5. 2018Byzantine-Robust Distributed Learning: Towards Optimal Statistical Ratescited by 698
  6. 2019Federated Learning with Differential Privacy: Algorithms and Performance Analysiscited by 528
  7. 2019Local Model Poisoning Attacks to Byzantine-Robust Federated Learningcited by 479
  8. 2018Spectral Signatures in Backdoor Attackscited by 457
  9. 2017Differentially Private Federated Learning: A Client Level Perspectivecited by 451
  10. 2020FLTrust: Byzantine-robust Federated Learning via Trust Bootstrappingcited by 330
  11. 2018The Hidden Vulnerability of Distributed Learning in Byzantiumcited by 324
  12. 2019Robust Aggregation for Federated Learningcited by 314
20 more
  1. 2020Attack of the Tails: Yes, You Really Can Backdoor Federated Learningcited by 307
  2. 2020Data Poisoning Attacks Against Federated Learning Systemscited by 266
  3. 2019Can You Really Backdoor Federated Learning?cited by 250
  4. 2021Federated Learning for Internet of Things: A Comprehensive Surveycited by 247
  5. 2020Blind Backdoors in Deep Learning Modelscited by 174
  6. 2018Mitigating Sybils in Federated Learning Poisoningcited by 158
  7. 2021Federated Learning for Open Bankingcited by 138
  8. 2022FLDetector: Defending Federated Learning Against Model Poisoning Attacks via Detecting Malicious Clientscited by 119
  9. 2021Back to the Drawing Board: A Critical Evaluation of Poisoning Attacks on Production Federated Learningcited by 116
  10. 2019Robust Anomaly Detection and Backdoor Attack Detection Via Differential Privacycited by 93
  11. 2021CRFL: Certifiably Robust Federated Learning against Backdoor Attackscited by 91
  12. 2020Learning to Detect Malicious Clients for Robust Federated Learningcited by 86
  13. 2020Defending against Backdoors in Federated Learning with Robust Learning Ratecited by 82
  14. 2020BaFFLe: Backdoor detection via Feedback-based Federated Learningcited by 52
  15. 2018Federated Learning in Distributed Medical Databases: Meta-Analysis of Large-Scale Subcortical Brain Datacited by 46
  16. 2021Physical Adversarial Attacks on an Aerial Imagery Object Detectorcited by 35
  17. 2018Universal Multi-Party Poisoning Attackscited by 17
  18. 2019The Best Defense Is a Good Offense: Adversarial Attacks to Avoid Modulation Detectioncited by 17
  19. 2021EvilModel: Hiding Malware Inside of Neural Network Modelscited by 15
  20. 2021Untargeted Poisoning Attack Detection in Federated Learning via Behavior Attestationcited by 12

Built on by

Not cited yet.