Privacy Preservation in Federated Learning: An insightful survey from the GDPR Perspective
arXiv:2011.05411
Abstract
Along with the blooming of AI and Machine Learning-based applications and services, data privacy and security have become a critical challenge. Conventionally, data is collected and aggregated in a data centre on which machine learning models are trained. This centralised approach has induced severe privacy risks to personal data leakage, misuse, and abuse. Furthermore, in the era of the Internet of Things and big data in which data is essentially distributed, transferring a vast amount of data to a data centre for processing seems to be a cumbersome solution. This is not only because of the difficulties in transferring and sharing data across data sources but also the challenges on complying with rigorous data protection regulations and complicated administrative procedures such as the EU General Data Protection Regulation (GDPR). In this respect, Federated learning (FL) emerges as a prospective solution that facilitates distributed collaborative learning without disclosing original training data whilst naturally complying with the GDPR. Recent research has demonstrated that retaining data and computation on-device in FL is not sufficient enough for privacy-guarantee. This is because ML model parameters exchanged between parties in an FL system still conceal sensitive information, which can be exploited in some privacy attacks. Therefore, FL systems shall be empowered by efficient privacy-preserving techniques to comply with the GDPR. This article is dedicated to surveying on the state-of-the-art privacy-preserving techniques which can be employed in FL in a systematic fashion, as well as how these techniques mitigate data security and privacy risks. Furthermore, we provide insights into the challenges along with prospective approaches following the GDPR regulatory guidelines that an FL system shall implement to comply with the GDPR.
arXiv comment21 pages, 8 figures, 2 tables
References in corpus (31)
- Adam: A Method for Stochastic Optimization
- Deep Learning with Differential Privacy
- Communication-Efficient Learning of Deep Networks from Decentralized Data
- An overview of gradient descent optimization algorithms
- Towards A Rigorous Science of Interpretable Machine Learning
- Federated Learning: Strategies for Improving Communication Efficiency
- Stochastic Backpropagation and Approximate Inference in Deep Generative Models
- Interpretable machine learning: definitions, methods, and applications
- Federated Learning with Non-IID Data
- Federated Optimization: Distributed Machine Learning for On-Device Intelligence
- Comprehensive Privacy Analysis of Deep Learning: Passive and Active White-box Inference Attacks against Centralized and Federated Learning
- Convergence of Edge Computing and Deep Learning: A Comprehensive Survey
- Understanding Black-box Predictions via Influence Functions
- Targeted Backdoor Attacks on Deep Learning Systems Using Data Poisoning
- Towards Federated Learning at Scale: System Design
- Revisiting Distributed Synchronous SGD
- On Large-Batch Training for Deep Learning: Generalization Gap and Sharp Minima
- Differentially Private Federated Learning: A Client Level Perspective
- Applied Federated Learning: Improving Google Keyboard Query Suggestions
- Communication Efficient Distributed Optimization using an Approximate Newton-type Method
- Mitigating Sybils in Federated Learning Poisoning
- Is feature selection secure against training data poisoning?
- Protection Against Reconstruction and Its Applications in Private Federated Learning
- Inverting Gradients -- How easy is it to break privacy in federated learning?
- Practical Secure Aggregation for Federated Learning on User-Held Data
- Deep Learning for Case-Based Reasoning through Prototypes: A Neural Network that Explains Its Predictions
- Federated Multi-Task Learning
- GossipGraD: Scalable Deep Learning using Gossip Communication based Asynchronous Gradient Descent
- COLA: Decentralized Linear Learning
- LDP-FL: Practical Private Aggregation in Federated Learning with Local Differential Privacy
- DRACO: Byzantine-resilient Distributed Training via Redundant Gradients