Resilience of Wireless Ad Hoc Federated Learning against Model Poisoning Attacks
Not on the map. Why?
Abstract (arXiv)
Wireless ad hoc federated learning (WAFL) is a fully decentralized collaborative machine learning framework organized by opportunistically encountered mobile nodes. Compared to conventional federated learning, WAFL performs model training by weakly synchronizing the model parameters with others, and this shows great resilience to a poisoned model injected by an attacker. In this paper, we provide our theoretical analysis of the WAFL's resilience against model poisoning attacks, by formulating the force balance between the poisoned model and the legitimate model. According to our experiments, we confirmed that the nodes directly encountered the attacker has been somehow compromised to the poisoned model but other nodes have shown great resilience. More importantly, after the attacker has left the network, all the nodes have finally found stronger model parameters combined with the poisoned model. Most of the attack-experienced cases achieved higher accuracy than the no-attack-experienced cases.
Key facts. Cited by 2 papers in the map (data through 14 Oct 2026). Builds on 15 of its 22 references that are in the map. First posted on arXiv 7 Nov 2022.
Builds on
15 of 22 references.
References · 15
- 2019Federated Learning: Challenges, Methods, and Future Directionscited by 1,538
- 2016Federated Learning: Strategies for Improving Communication Efficiencycited by 1,475
- 2018How To Backdoor Federated Learningcited by 765
- 2020Inverting Gradients -- How easy is it to break privacy in federated learning?cited by 712
- 2019Local Model Poisoning Attacks to Byzantine-Robust Federated Learningcited by 493
- 2021Towards Personalized Federated Learningcited by 464
- 2020Backdoor Learning: A Surveycited by 426
- 2020Attack of the Tails: Yes, You Really Can Backdoor Federated Learningcited by 309
- 2020A Blockchain-based Decentralized Federated Learning Framework with Committee Consensuscited by 84
- 2020Defending against Backdoors in Federated Learning with Robust Learning Ratecited by 82
- 2018Technical Report: When Does Machine Learning FAIL? Generalized Transferability for Evasion and Poisoning Attackscited by 81
- 2021Provably Secure Federated Learning against Malicious Clientscited by 63
3 more
- 2022Semi-Targeted Model Poisoning Attack on Federated Learning via Backward Error Analysiscited by 9
- 2022Wireless Ad Hoc Federated Learning: A Fully Distributed Cooperative Machine Learningcited by 4
- 2021Information Stealing in Federated Learning Systems Based on Generative Adversarial Networkscited by 3
Built on by
Citing papers per year: 2024: 1; 2025: 1.
2 papers.