paper-with-me

홈 › Papers

MPAF: Model Poisoning Attacks to Federated Learning based on Fake Clients

2022-03-16 · Xiaoyu Cao, Neil Zhenqiang Gong

Existing model poisoning attacks to federated learning assume that an attacker has access to a large fraction of compromised genuine clients. However, such assumption is not realistic in production federated learning systems that involve millions of clients. In this work, we propose the first Model Poisoning Attack based on Fake clients called MPAF. Specifically, we assume the attacker injects fake clients to a federated learning system and sends carefully crafted fake local model updates to the cloud server during training, such that the learnt global model has low accuracy for many indiscriminate test inputs. Towards this goal, our attack drags the global model towards an attacker-chosen base model that has low accuracy. Specifically, in each round of federated learning, the fake clients craft fake local model updates that point to the base model and scale them up to amplify their impact before sending them to the cloud server. Our experiments show that MPAF can significantly decrease the test accuracy of the global model, even if classical defenses and norm clipping are adopted, highlighting the need for more advanced defenses.

📄 PDF Abstract BibTeX arXiv:2203.08669

Code (1)

yjlee22/byzantinefl pytorch

Tasks

Federated LearningModel Poisoning

Methods 이 논문이 사용한 방법론

BASE 설명 없음

Similar Papers 제목 키워드 기반

FLCert: Provably Secure Federated Learning against Poisoning Attacks

2022-10-02 · Xiaoyu Cao, Zaixi Zhang, Jinyuan Jia, Neil Zhenqiang Gong

Due to its distributed nature, federated learning is vulnerable to poisoning attacks, in which malicious clients poison the training process via manipulating their local training data and/or local model updates sent to t…

Federated Learning

Poisoning Attacks and Defenses to Federated Unlearning

2025-01-29 · Wenbin Wang, Qiwen Ma, Zifan Zhang, Yuchen Liu 외

Federated learning allows multiple clients to collaboratively train a global model with the assistance of a server. However, its distributed nature makes it susceptible to poisoning attacks, where malicious clients can c…

Federated Learning

CATFL: Certificateless Authentication-based Trustworthy Federated Learning for 6G Semantic Communications

2023-02-01 · Gaolei Li, YuanYuan Zhao, Yi Li

Federated learning (FL) provides an emerging approach for collaboratively training semantic encoder/decoder models of semantic communication systems, without private user data leaving the devices. Most existing studies o…

Data PoisoningDecoderFederated LearningManagement+2

FedRecover: Recovering from Poisoning Attacks in Federated Learning using Historical Information

2022-10-20 · Xiaoyu Cao, Jinyuan Jia, Zaixi Zhang, Neil Zhenqiang Gong

Federated learning is vulnerable to poisoning attacks in which malicious clients poison the global model via sending malicious model updates to the server. Existing defenses focus on preventing a small number of maliciou…

Federated Learning

Poisoning Attacks and Defenses in Federated Learning: A Survey

2023-01-14 · Subhash Sagar, Chang-Sun Li, Seng W. Loke, Jinho Choi

Federated learning (FL) enables the training of models among distributed clients without compromising the privacy of training datasets, while the invisibility of clients datasets and the training process poses a variety …

Federated LearningSurvey