Small on-device models have been successfully trained with user-level differential privacy (DP) for next word prediction and image classification tasks in the past. However, existing methods can fail when directly applied to learn embedding models using supervised training data with a large class space. To achieve user-level DP for large image-to-embedding feature extractors, we propose DP-FedEmb, a variant of federated learning algorithms with per-user sensitivity control and noise addition, to train from user-partitioned data centralized in the datacenter. DP-FedEmb combines virtual clients, partial aggregation, private local fine-tuning, and public pretraining to achieve strong privacy utility trade-offs. We apply DP-FedEmb to train imag...
Federated Learning (FL) is a distributed machine learning approach that safeguards privacy by creati...
While modern machine learning models rely on increasingly large training datasets, data is often lim...
Many existing privacy-enhanced speech emotion recognition (SER) frameworks focus on perturbing the o...
Federated Learning (FL) is a technique to train models using data distributed across devices. Differ...
Differentially Private methods for training Deep Neural Networks (DNNs) have progressed recently, in...
Leveraging transfer learning has recently been shown to be an effective strategy for training large ...
Visual Prompting (VP) is an emerging and powerful technique that allows sample-efficient adaptation ...
Previous work on user-level differential privacy (DP) [Ghazi et al. NeurIPS 2021, Bun et al. STOC 20...
Existing approaches for training neural networks with user-level differential privacy (e.g., DP Fede...
We study the problem of differentially private (DP) fine-tuning of large pre-trained models -- a rec...
Federated learning (FL) that enables edge devices to collaboratively learn a shared model while keep...
A well-known algorithm in privacy-preserving ML is differentially private stochastic gradient descen...
Data is coined to be the new oil due to the increasing awareness of its value in a myriad of applica...
In this paper, we introduce a data augmentation-based defense strategy for preventing the reconstruc...
The collection of individuals' data has become commonplace in many industries. Local differential pr...
Federated Learning (FL) is a distributed machine learning approach that safeguards privacy by creati...
While modern machine learning models rely on increasingly large training datasets, data is often lim...
Many existing privacy-enhanced speech emotion recognition (SER) frameworks focus on perturbing the o...
Federated Learning (FL) is a technique to train models using data distributed across devices. Differ...
Differentially Private methods for training Deep Neural Networks (DNNs) have progressed recently, in...
Leveraging transfer learning has recently been shown to be an effective strategy for training large ...
Visual Prompting (VP) is an emerging and powerful technique that allows sample-efficient adaptation ...
Previous work on user-level differential privacy (DP) [Ghazi et al. NeurIPS 2021, Bun et al. STOC 20...
Existing approaches for training neural networks with user-level differential privacy (e.g., DP Fede...
We study the problem of differentially private (DP) fine-tuning of large pre-trained models -- a rec...
Federated learning (FL) that enables edge devices to collaboratively learn a shared model while keep...
A well-known algorithm in privacy-preserving ML is differentially private stochastic gradient descen...
Data is coined to be the new oil due to the increasing awareness of its value in a myriad of applica...
In this paper, we introduce a data augmentation-based defense strategy for preventing the reconstruc...
The collection of individuals' data has become commonplace in many industries. Local differential pr...
Federated Learning (FL) is a distributed machine learning approach that safeguards privacy by creati...
While modern machine learning models rely on increasingly large training datasets, data is often lim...
Many existing privacy-enhanced speech emotion recognition (SER) frameworks focus on perturbing the o...