paper-with-me

Papers

Mitigating Backdoor Attacks in Federated Learning via Flipping Weight Updates of Low-Activation Input Neurons

2024-08-16 · Binbin Ding, Penghui Yang, Zeqing Ge, Shengjun Huang

Federated learning enables multiple clients to collaboratively train machine learning models under the overall planning of the server while adhering to privacy requirements. However, the server cannot directly oversee the local training process, creating an opportunity for malicious clients to introduce backdoors. Existing research shows that backdoor attacks activate specific neurons in the compromised model, which remain dormant when processing clean data. Leveraging this insight, we propose a method called Flipping Weight Updates of Low-Activation Input Neurons (FLAIN) to defend against backdoor attacks in federated learning. Specifically, after completing global training, we employ an auxiliary dataset to identify low-activation input neurons and flip the associated weight updates. We incrementally raise the threshold for low-activation inputs and flip the weight updates iteratively, until the performance degradation on the auxiliary data becomes unacceptable. Extensive experiments validate that our method can effectively reduce the success rate of backdoor attacks to a low level in various attack scenarios including those with non-IID data distribution or high MCRs, causing only minimal performance degradation on clean data.

📄 PDF Abstract BibTeX arXiv:2408.08655

Code (0)

등록된 구현이 없습니다.

Tasks

Federated Learning

Methods 이 논문이 사용한 방법론

FLIP https://developer.nvidia.com/blog/flip-a-difference-evaluator-for-alternating-images/

Similar Papers 제목 키워드 기반

Attack-Resistant Federated Learning with Residual-based Reweighting

2019-12-24 · Shuhao Fu, Chulin Xie, Bo Li, Qifeng Chen

Federated learning has a variety of applications in multiple domains by utilizing private training data stored on different devices. However, the aggregation process in federated learning is highly vulnerable to adversar…

Federated Learningregression

Mitigating Backdoor Attacks in Federated Learning

2020-10-28 · Chen Wu, Xian Yang, Sencun Zhu, Prasenjit Mitra

Malicious clients can attack federated learning systems using malicious data, including backdoor samples, during the training phase. The compromised global model will perform well on the validation dataset designed for t…

Federated Learning

DeepSight: Mitigating Backdoor Attacks in Federated Learning Through Deep Model Inspection

2022-01-03 · Phillip Rieger, Thien Duc Nguyen, Markus Miettinen, Ahmad-Reza Sadeghi

Federated Learning (FL) allows multiple clients to collaboratively train a Neural Network (NN) model on their private data without revealing the data. Recently, several targeted poisoning attacks against FL have been int…

Federated Learning

Mitigating Sybils in Federated Learning Poisoning

2018-08-14 · Clement Fung, Chris J. M. Yoon, Ivan Beschastnikh

Machine learning (ML) over distributed multi-party data is required for a variety of domains. Existing approaches, such as federated learning, collect the outputs computed by a group of devices at a central aggregator an…

DiversityFederated LearningModel Poisoning

SAB:A Stealing and Robust Backdoor Attack based on Steganographic Algorithm against Federated Learning

2024-08-25 · Weida Xu, Yang Xu, Sicong Zhang

Federated learning, an innovative network architecture designed to safeguard user privacy, is gaining widespread adoption in the realm of technology. However, given the existence of backdoor attacks in federated learning…

Backdoor Attackbackdoor defenseFederated Learning