BlockFLow: An Accountable and Privacy-Preserving Solution for Federated Learning
Federated learning enables the development of a machine learning model among collaborating agents without requiring them to share their underlying data. However, malicious agents who train on random data, or worse, on datasets with the result classes inverted, can weaken the combined model. BlockFLow is an accountable federated learning system that is fully decentralized and privacy-preserving. Its primary goal is to reward agents proportional to the quality of their contribution while protecting the privacy of the underlying datasets and being resilient to malicious adversaries. Specifically, BlockFLow incorporates differential privacy, introduces a novel auditing mechanism for model contribution, and uses Ethereum smart contracts to incentivize good behavior. Unlike existing auditing and accountability methods for federated learning systems, our system does not require a centralized test dataset, sharing of datasets between the agents, or one or more trusted auditors; it is fully decentralized and resilient up to a 50% collusion attack in a malicious trust model. When run on the public Ethereum blockchain, BlockFLow uses the results from the audit to reward parties with cryptocurrency based on the quality of their contribution. We evaluated BlockFLow on two datasets that offer classification tasks solvable via logistic regression models. Our results show that the resultant auditing scores reflect the quality of the honest agents' datasets. Moreover, the scores from dishonest agents are statistically lower than those from the honest agents. These results, along with the reasonable blockchain costs, demonstrate the effectiveness of BlockFLow as an accountable federated learning system.
Code (0)
등록된 구현이 없습니다.
Tasks
Federated LearningPrivacy PreservingMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
When Crowdsensing Meets Federated Learning: Privacy-Preserving Mobile Crowdsensing System
Mobile crowdsensing (MCS) is an emerging sensing data collection pattern with scalability, low deployment cost, and distributed characteristics. Traditional MCS systems suffer from privacy concerns and fair reward distri…
Federated LearningPrivacy PreservingHybridAlpha: An Efficient Approach for Privacy-Preserving Federated Learning
Federated learning has emerged as a promising approach for collaborative and privacy-preserving learning. Participants in a federated learning process cooperatively train a model by exchanging model parameters instead of…
Federated LearningPrivacy PreservingTowards Privacy-Preserving Data-Driven Education: The Potential of Federated Learning
The increasing adoption of data-driven applications in education such as in learning analytics and AI in education has raised significant privacy and data protection concerns. While these challenges have been widely disc…
Federated LearningPrivacy PreservingVision Through the Veil: Differential Privacy in Federated Learning for Medical Image Classification
The proliferation of deep learning applications in healthcare calls for data aggregation across various institutions, a practice often associated with significant privacy concerns. This concern intensifies in medical ima…
Federated Learningimage-classificationImage ClassificationMedical Image Analysis+2Federated Continual Recommendation
The increasing emphasis on privacy in recommendation systems has led to the adoption of Federated Learning (FL) as a privacy-preserving solution, enabling collaborative training without sharing user data. While Federated…
Recommendation SystemsFederated LearningContinual Learning