Related papers: Privacy-Preserving Transformers: SwiftKey's Differ…
This work studies formal utility and privacy guarantees for a simple multiplicative database transformation, where the data are compressed by a random linear or affine transformation, reducing the number of data records substantially, while…
We present new mechanisms for \emph{label differential privacy}, a relaxation of differentially private machine learning that only protects the privacy of the labels in the training set. Our mechanisms cluster the examples in the training…
Machine learning models are increasingly made available to the masses through public query interfaces. Recent academic work has demonstrated that malicious users who can query such models are able to infer sensitive information about…
Reinforcement learning (RL) is a powerful tool for sequential decision-making, but its application is often hindered by privacy concerns arising from its interaction data. This challenge is particularly acute in advanced networked systems,…
Prior work on differential privacy analysis of randomized SGD algorithms relies on composition theorems, where the implicit (unrealistic) assumption is that the internal state of the iterative algorithm is revealed to the adversary. As a…
Neural machine translation (NMT) is a widely popular text generation task, yet there is a considerable research gap in the development of privacy-preserving NMT models, despite significant data privacy concerns for NMT systems.…
Differentially private (DP) transfer learning, i.e., fine-tuning a pretrained model on private data, is the current state-of-the-art approach for training large models under privacy constraints. We focus on two key hyperparameters in this…
Fine-tuning large language models on sensitive data poses significant privacy risks, as membership inference attacks can reveal whether individual records were used during training. While Differential Privacy (DP) provides formal…
Train machine learning models on sensitive user data has raised increasing privacy concerns in many areas. Federated learning is a popular approach for privacy protection that collects the local gradient information instead of real data.…
In this paper, we focus on preserving differential privacy (DP) in continual learning (CL), in which we train ML models to learn a sequence of new tasks while memorizing previous tasks. We first introduce a notion of continual adjacent…
Traditionally, the random noise is equally injected when training with different data instances in the field of differential privacy (DP). In this paper, we first give sharper excess risk bounds of DP stochastic gradient descent (SGD)…
Large language models (LLMs) are trained on vast datasets that may contain sensitive information. Differential privacy (DP), the de facto standard for formal privacy guarantees, provides a principled framework for training LLMs with…
We consider a refinement of differential privacy --- per instance differential privacy (pDP), which captures the privacy of a specific individual with respect to a fixed data set. We show that this is a strict generalization of the standard…
Current practices for reporting the level of differential privacy (DP) protection for machine learning (ML) algorithms such as DP-SGD provide an incomplete and potentially misleading picture of the privacy guarantees. For instance, if only…
Large language models (LLMs) trained on web-scale corpora can memorize sensitive training data, posing significant privacy risks. Differential privacy (DP) has emerged as a principled framework that limits the influence of individual data…
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…
Differential privacy (DP) provides a provable framework for protecting individuals by customizing a random mechanism over a privacy-sensitive dataset. Deep learning models have demonstrated privacy risks in model exposure as an established…
Training machine learning models based on neural networks requires large datasets, which may contain sensitive information. The models, however, should not expose private information from these datasets. Differentially private SGD [DP-SGD]…
The Transformer has emerged as a versatile and effective architecture with broad applications. However, it still remains an open problem how to efficiently train a Transformer model of high utility with differential privacy guarantees. In…
Synthetic tabular data generation with differential privacy is a crucial problem to enable data sharing with formal privacy. Despite a rich history of methodological research and development, developing differentially private tabular data…