Related papers: A Shuffling Framework for Local Differential Priva…
Federated learning has emerged as an attractive approach to protect data privacy by eliminating the need for sharing clients' data while reducing communication costs compared with centralized machine learning algorithms. However, recent…
The *shuffle model* is a powerful tool to amplify the privacy guarantees of the *local model* of differential privacy. In contrast to the fully decentralized manner of guaranteeing privacy in the local model, the shuffle model requires a…
Latent Dirichlet Allocation (LDA) is a popular topic modeling technique for hidden semantic discovery of text data and serves as a fundamental tool for text analysis in various applications. However, the LDA model as well as the training…
Personalized privacy becomes critical in deep learning for Trustworthy AI. While Differentially Private Stochastic Gradient Descent (DP-SGD) is widely used in deep learning methods supporting privacy, it provides the same level of privacy…
Federated Learning (FL) allows multiple participants to train machine learning models collaboratively by keeping their datasets local while only exchanging model updates. Alas, this is not necessarily free from privacy and robustness…
Machine learning models are vulnerable to data inference attacks, such as membership inference and model inversion attacks. In these types of breaches, an adversary attempts to infer a data record's membership in a dataset or even…
Differentially private federated learning (DP-FL) is a promising technique for collaborative model training while ensuring provable privacy for clients. However, optimizing the tradeoff between privacy and accuracy remains a critical…
Federated learning (FL) as one of the novel branches of distributed machine learning (ML), develops global models through a private procedure without direct access to local datasets. However, access to model updates (e.g. gradient updates…
Decentralized Federated Learning (DFL) enables collaborative model training without a central server, but it remains vulnerable to privacy leakage because shared model updates can expose sensitive information through inversion,…
We consider the problem of designing scalable, robust protocols for computing statistics about sensitive data. Specifically, we look at how best to design differentially private protocols in a distributed setting, where each user holds a…
The vanilla Differentially-Private Stochastic Gradient Descent (DP-SGD), including DP-Adam and other variants, ensures the privacy of training data by uniformly distributing privacy costs across training steps. The equivalent privacy costs…
The emergence and evolution of Local Differential Privacy (LDP) and its various adaptations play a pivotal role in tackling privacy issues related to the vast amounts of data generated by intelligent devices, which are crucial for…
This work studies differential privacy in the context of the recently proposed shuffle model. Unlike in the local model, where the server collecting privatized data from users can track back an input to a specific user, in the shuffle model…
Federated learning (FL) aims to collaboratively train the global model in a distributed manner by sharing the model parameters from local clients to a central server, thereby potentially protecting users' private information. Nevertheless,…
The popularity of federated learning comes from the possibility of better scalability and the ability for participants to keep control of their data, improving data security and sovereignty. Unfortunately, sharing model updates also creates…
The software-based implementation of differential privacy mechanisms has been shown to be neither friendly for lightweight devices nor secure against side-channel attacks. In this work, we aim to develop a hardware-based technique to…
To defend the inference attacks and mitigate the sensitive information leakages in Federated Learning (FL), client-level Differentially Private FL (DPFL) is the de-facto standard for privacy protection by clipping local updates and adding…
In this paper, we address the problem of privacy-preserving distributed learning and the evaluation of machine-learning models by analyzing it in the widespread MapReduce abstraction that we extend with privacy constraints. We design…
In the recent decades, the advance of information technology and abundant personal data facilitate the application of algorithmic personalized pricing. However, this leads to the growing concern of potential violation of privacy due to…
Differential Privacy (DP) provides an elegant mathematical framework for defining a provable disclosure risk in the presence of arbitrary adversaries; it guarantees that whether an individual is in a database or not, the results of a DP…