Related papers: Differentially Private Distributed Online Learning
This paper studies decentralized federated learning algorithms in wireless IoT networks. The traditional parameter server architecture for federated learning faces some problems such as low fault tolerance, large communication overhead and…
Local differential privacy is a widely studied restriction on distributed algorithms that collect aggregates about sensitive user data, and is now deployed in several large systems. We initiate a systematic study of a fundamental limitation…
In domains such as health care and finance, shortage of labeled data and computational resources is a critical issue while developing machine learning algorithms. To address the issue of labeled data scarcity in training and deployment of…
We consider the problem of reinforcing federated learning with formal privacy guarantees. We propose to employ Bayesian differential privacy, a relaxation of differential privacy for similarly distributed data, to provide sharper privacy…
Differential Privacy has become a widely popular method for data protection in machine learning, especially since it allows formulating strict mathematical privacy guarantees. This survey provides an overview of the state-of-the-art of…
Differential privacy is one of the methods to solve the problem of privacy protection in federated learning. Setting the same privacy budget for each round will result in reduced accuracy in training. The existing methods of the adjustment…
In this work, we analyze the generalization ability of distributed online learning algorithms under stationary and non-stationary environments. We derive bounds for the excess-risk attained by each node in a connected network of learners…
In recent years, machine learning techniques utilizing large-scale datasets have achieved remarkable performance. Differential privacy, by means of adding noise, provides strong privacy guarantees for such learning algorithms. The cost of…
We consider training machine learning models using Training data located on multiple private and geographically-scattered servers with different privacy settings. Due to the distributed nature of the data, communicating with all…
Much of the literature on differential privacy focuses on item-level privacy, where loosely speaking, the goal is to provide privacy per item or training example. However, recently many practical applications such as federated learning…
This paper investigates the privacy-preserving distributed optimization problem, aiming to protect agents' private information from potential attackers during the optimization process. Gradient tracking, an advanced technique for improving…
Federated learning is a distributed learning setting where the main aim is to train machine learning models without having to share raw data but only what is required for learning. To guarantee training data privacy and high-utility models,…
The performance of differentially private machine learning can be boosted significantly by leveraging the transfer learning capabilities of non-private models pretrained on large public datasets. We critically review this approach. We…
Decentralized optimization has become a standard paradigm for solving large-scale decision-making problems and training large machine learning models without centralizing data. However, this paradigm introduces new privacy and security…
Privacy-preserving federated learning enables a population of distributed clients to jointly learn a shared model while keeping client training data private, even from an untrusted server. Prior works do not provide efficient solutions that…
Commercial companies that collect user data on a large scale have been the main beneficiaries of this trend since the success of deep learning techniques is directly proportional to the amount of data available for training. Massive data…
Machine learning (ML) models have been shown to leak private information from their training datasets. Differential Privacy (DP), typically implemented through the differential private stochastic gradient descent algorithm (DP-SGD), has…
In this paper, an adjustment to the original differentially private stochastic gradient descent (DPSGD) algorithm for deep learning models is proposed. As a matter of motivation, to date, almost no state-of-the-art machine learning…
Scientific collaborations benefit from collaborative learning of distributed sources, but remain difficult to achieve when data are sensitive. In recent years, privacy preserving techniques have been widely studied to analyze distributed…
Deep learning often requires a large amount of data. In real-world applications, e.g., healthcare applications, the data collected by a single organization (e.g., hospital) is often limited, and the majority of massive and diverse data is…