Search Results for author:
Found 17 papers, 9 papers with code
Green Federated Learning
The rapid progress of AI is fueled by increasingly large and computationally intensive machine learning models and datasets.
Reconciling Security and Communication Efficiency in Federated Learning
Cross-device Federated Learning is an increasingly popular machine learning setting to train a model by leveraging a large population of client devices with high privacy and security guarantees.
FEL: High Capacity Learning for Recommendation and Ranking via Federated Ensemble Learning
Despite FL's initial success, many important deep learning use cases, such as ranking and recommendation tasks, have been limited from on-device learning.
Defending against Reconstruction Attacks with Rényi Differential Privacy
Reconstruction attacks allow an adversary to regenerate data samples of the training set using access to only a trained model.
Opacus: User-Friendly Differential Privacy Library in PyTorch
We introduce Opacus, a free, open-source PyTorch library for training deep learning models with differential privacy (hosted at opacus. ai).
Antipodes of Label Differential Privacy: PATE and ALIBI
We propose two novel approaches based on, respectively, the Laplace mechanism and the PATE framework, and demonstrate their effectiveness on standard benchmarks.
Wide Network Learning with Differential Privacy
Despite intense interest and considerable effort, the current generation of neural networks suffers a significant loss of accuracy under most practically relevant privacy training regimes.
Cryptanalytic Extraction of Neural Network Models
We argue that the machine learning problem of model extraction is actually a cryptanalytic problem in disguise, and should be studied as such.
Rényi Differential Privacy of the Sampled Gaussian Mechanism
The Sampled Gaussian Mechanism (SGM)---a composition of subsampling and the additive Gaussian noise---has been successfully used in a number of machine learning applications.
That which we call private
Instead, the definitions so named are the basis of refinements and more advanced analyses of the worst-case implications of attackers---without any change assumed in attackers' powers.
A General Approach to Adding Differential Privacy to Iterative Training Procedures
In this work we address the practical challenges of training machine learning models on privacy-sensitive datasets by introducing a modular approach that minimizes changes to training algorithms, provides a variety of configuration strategies for the privacy mechanism, and then isolates and simplifies the critical logic that computes the final privacy guarantees.
Amplification by Shuffling: From Local to Central Differential Privacy via Anonymity
We study the collection of such statistics in the local differential privacy (LDP) model, and describe an algorithm whose privacy cost is polylogarithmic in the number of changes to a user's value.
Privacy Amplification by Iteration
In addition, we demonstrate that we can achieve guarantees similar to those obtainable using the privacy-amplification-by-sampling technique in several natural settings where that technique cannot be applied.
On the Protection of Private Information in Machine Learning Systems: Two Recent Approaches
The recent, remarkable growth of machine learning has led to intense interest in the privacy of the data on which machine learning relies, and to new techniques for preserving privacy.
Renyi Differential Privacy
We propose a natural relaxation of differential privacy based on the Renyi divergence.
Cryptography and Security
Deep Learning with Differential Privacy
Machine learning techniques based on neural networks are achieving remarkable results in a wide variety of domains.
