paper-with-me

Papers

Resilience of Wireless Ad Hoc Federated Learning against Model Poisoning Attacks

2022-11-07 · Naoya Tezuka, Hideya Ochiai, Yuwei Sun, Hiroshi Esaki

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.

📄 PDF Abstract BibTeX arXiv:2211.03489

Code (0)

등록된 구현이 없습니다.

Tasks

Federated LearningModel Poisoning

Methods 이 논문이 사용한 방법론

HOC 설명 없음

Similar Papers 제목 키워드 기반

Resilience in Online Federated Learning: Mitigating Model-Poisoning Attacks via Partial Sharing

2024-03-19 · Ehsan Lari, Reza Arablouei, Vinay Chakravarthi Gogineni, Stefan Werner

Federated learning (FL) allows training machine learning models on distributed data without compromising privacy. However, FL is vulnerable to model-poisoning attacks where malicious clients tamper with their local model…

Federated LearningModel Poisoning

Federated Learning in Adversarial Environments: Testbed Design and Poisoning Resilience in Cybersecurity

2024-09-15 · Hao Jian Huang, Hakan T. Otal, M. Abdullah Canbaz

This paper presents the design and implementation of a Federated Learning (FL) testbed, focusing on its application in cybersecurity and evaluating its resilience against poisoning attacks. Federated Learning allows mult…

Federated LearningIntrusion Detection

Towards Sybil Resilience in Decentralized Learning

2023-06-26 · Thomas Werthenbach, Johan Pouwelse

Federated learning is a privacy-enforcing machine learning technology but suffers from limited scalability. This limitation mostly originates from the internet connection and memory capacity of the central parameter serv…

Adversarial AttackFederated Learning

An Equivalence Between Data Poisoning and Byzantine Gradient Attacks

2022-02-17 · Sadegh Farhadkhani, Rachid Guerraoui, Lê-Nguyên Hoang, Oscar Villemaud

To study the resilience of distributed learning, the "Byzantine" literature considers a strong threat model where workers can report arbitrary gradients to the parameter server. Whereas this model helped obtain several f…

Data PoisoningFederated LearningPersonalized Federated Learning

Robust Federated Recommendation System

2020-06-15 · Chen Chen, Jingfeng Zhang, Anthony K. H. Tung, Mohan Kankanhalli 외

Federated recommendation systems can provide good performance without collecting users' private data, making them attractive. However, they are susceptible to low-cost poisoning attacks that can degrade their performance…

Recommendation Systems