Related papers: CryptoNAS: Private Inference on a ReLU Budget
Today's cloud vendors are competing to provide various offerings to simplify and accelerate AI service deployment. However, cloud users always have concerns about the confidentiality of their runtime data, which are supposed to be processed…
Traditional approaches to differential privacy assume a fixed privacy requirement $\epsilon$ for a computation, and attempt to maximize the accuracy of the computation subject to the privacy constraint. As differential privacy is…
We introduce PrivPy, a practical privacy-preserving collaborative computation framework, especially optimized for machine learning tasks. PrivPy provides an easy-to-use and highly compatible Python programming front-end which supports…
Differentially private stochastic gradient descent privatizes model training by injecting noise into each iteration, where the noise magnitude increases with the number of model parameters. Recent works suggest that we can reduce the noise…
A Private Repetition algorithm takes as input a differentially private algorithm with constant success probability and boosts it to one that succeeds with high probability. These algorithms are closely related to private metaselection…
We establish a simple connection between robust and differentially-private algorithms: private mechanisms which perform well with very high probability are automatically robust in the sense that they retain accuracy even if a constant…
Users increasingly rely on large language models (LLMs) for personal, emotionally charged, and socially sensitive conversations. However, prompts sent to cloud-hosted models can contain personally identifiable information (PII) that users…
MLaaS Service Providers (SPs) holding a Neural Network would like to keep the Neural Network weights secret. On the other hand, users wish to utilize the SPs' Neural Network for inference without revealing their data. Multi-Party…
Emerging neural networks based machine learning techniques such as deep learning and its variants have shown tremendous potential in many application domains. However, they raise serious privacy concerns due to the risk of leakage of highly…
The performance of modern machine learning systems depends on access to large, high-quality datasets, often sourced from user-generated content or proprietary, domain-specific corpora. However, these rich datasets inherently contain…
We are witnessing an increasing trend towardsusing Machine Learning (ML) based prediction systems, span-ning across different application domains, including productrecommendation systems, personal assistant devices, facialrecognition, etc.…
Certified unlearning based on differential privacy offers strong guarantees but remains largely impractical: the noisy fine-tuning approaches proposed so far achieve these guarantees but severely reduce model accuracy. We propose sequential…
Increasing interest in privacy-preserving machine learning has led to new and evolved approaches for generating private synthetic data from undisclosed real data. However, mechanisms of privacy preservation can significantly reduce the…
Broad adoption of machine learning techniques has increased privacy concerns for models trained on sensitive data such as medical records. Existing techniques for training differentially private (DP) models give rigorous privacy guarantees,…
This paper introduces a novel, computationally-efficient algorithm for predictive inference (PI) that requires no distributional assumptions on the data and can be computed faster than existing bootstrap-type methods for neural networks.…
In recent years, there have been many cloud-based machine learning services, where well-trained models are provided to users on a pay-per-query scheme through a prediction API. The emergence of these services motivates this work, where we…
The literature on differential privacy almost invariably assumes that the data to be analyzed are fully observed. In most practical applications this is an unrealistic assumption. A popular strategy to address this problem is imputation, in…
With the growing use of camera devices, the industry has many image datasets that provide more opportunities for collaboration between the machine learning community and industry. However, the sensitive information in the datasets…
In machine learning, classification models need to be trained in order to predict class labels. When the training data contains personal information about individuals, collecting training data becomes difficult due to privacy concerns.…
We develop a privatised stochastic variational inference method for Latent Dirichlet Allocation (LDA). The iterative nature of stochastic variational inference presents challenges: multiple iterations are required to obtain accurate…