Related papers: Differentially-Private Text Rewriting reshapes Lin…

With the increasing applications of language models, it has become crucial to protect these models from leaking private information. Previous work has attempted to tackle this challenge by training RNN-based language models with…

Large language models trained on clinical text risk exposing sensitive patient information, yet differential privacy (DP) methods often severely degrade the diagnostic accuracy needed for deployment. Despite rapid progress in DP…

Machine learning models should not reveal particular information that is not otherwise accessible. Differential privacy provides a formal framework to mitigate privacy risks by ensuring that the inclusion or exclusion of any single data…

As large language models (LLMs) are increasingly trained on sensitive user data, understanding the fundamental cost of privacy in language learning becomes essential. We initiate the study of differentially private (DP) language…

Absolute anonymization, conceived as an irreversible transformation that prevents re-identification and sensitive value disclosure, has proven to be a broken promise. Consequently, modern data protection must shift toward a privacy-utility…

Differentially private (DP) mechanisms are difficult to interpret and calibrate because existing methods for mapping standard privacy parameters to concrete privacy risks -- re-identification, attribute inference, and data reconstruction --…

Noisy gradient descent and its variants are the predominant algorithms for differentially private machine learning. It is a fundamental question to quantify their privacy leakage, yet tight characterizations remain open even in the…

Accurately learning from user data while ensuring quantifiable privacy guarantees provides an opportunity to build better Machine Learning (ML) models while maintaining user trust. Recent literature has demonstrated the applicability of a…

Motivated by the increasing deployment of reinforcement learning in the real world, involving a large consumption of personal data, we introduce a differentially private (DP) policy gradient algorithm. We show that, in this setting, the…

This paper firstly proposes a simple yet efficient generalized approach to apply differential privacy to text representation (i.e., word embedding). Based on it, we propose a user-level approach to learn personalized differentially private…

Recent developments in deep learning have led to great success in various natural language processing (NLP) tasks. However, these applications may involve data that contain sensitive information. Therefore, how to achieve good performance…

With the use of personal devices connected to the Internet for tasks such as searches and shopping becoming ubiquitous, ensuring the privacy of the users of such services has become a requirement in order to build and maintain customer…

Local differential privacy (LDP) has become a central topic in data privacy research, offering strong privacy guarantees by perturbing user data at the source and removing the need for a trusted curator. However, the noise introduced by LDP…

Sharing real-world speech utterances is key to the training and deployment of voice-based services. However, it also raises privacy risks as speech contains a wealth of personal data. Speaker anonymization aims to remove speaker information…

The increasing adoption of large language models (LLMs) in cloud-based services has raised significant privacy concerns, as user inputs may inadvertently expose sensitive information. Existing text anonymization and de-identification…

Differential Privacy (DP) is an important privacy-enhancing technology for private machine learning systems. It allows to measure and bound the risk associated with an individual participation in a computation. However, it was recently…

Reconstruction attacks allow an adversary to regenerate data samples of the training set using access to only a trained model. It has been recently shown that simple heuristics can reconstruct data samples from language models, making this…

Differential privacy (DP) is applied when fine-tuning pre-trained large language models (LLMs) to limit leakage of training examples. While most DP research has focused on improving a model's privacy-utility tradeoff, some find that DP can…

Differential privacy (DP) has become the standard for private data analysis. Certain machine learning applications only require privacy protection for specific protected attributes. Using naive variants of differential privacy in such use…

One of the big challenges in machine learning applications is that training data can be different from the real-world data faced by the algorithm. In language modeling, users' language (e.g. in private messaging) could change in a year and…