Related papers: Just Fine-tune Twice: Selective Differential Priva…

To protect the privacy of individuals whose data is being shared, it is of high importance to develop methods allowing researchers and companies to release textual data while providing formal privacy guarantees to its originators. In the…

Fine-tuning has emerged as a critical process in leveraging Large Language Models (LLMs) for specific downstream tasks, enabling these models to achieve state-of-the-art performance across various domains. However, the fine-tuning process…

Differential privacy (DP) allows the quantification of privacy loss when the data of individuals is subjected to algorithmic processing such as machine learning, as well as the provision of objective privacy guarantees. However, while…

Differential privacy (DP) is a privacy-preserving paradigm that protects the training data when training deep learning models. Critically, the performance of models is determined by the training hyperparameters, especially those of the…

We give simpler, sparser, and faster algorithms for differentially private fine-tuning of large-scale pre-trained language models, which achieve the state-of-the-art privacy versus utility tradeoffs on many standard NLP tasks. We propose a…

Training generative models with differential privacy (DP) typically involves injecting noise into gradient updates or adapting the discriminator's training procedure. As a result, such approaches often struggle with hyper-parameter tuning…

Federated learning has emerged as an attractive approach to protect data privacy by eliminating the need for sharing clients' data while reducing communication costs compared with centralized machine learning algorithms. However, recent…

Federated learning (FL) as one of the novel branches of distributed machine learning (ML), develops global models through a private procedure without direct access to local datasets. However, access to model updates (e.g. gradient updates…

While modern machine learning models rely on increasingly large training datasets, data is often limited in privacy-sensitive domains. Generative models trained with differential privacy (DP) on sensitive data can sidestep this challenge,…

Large language models (LLMs) do not preserve privacy at inference-time. The LLM's outputs can inadvertently reveal information about the model's context, which presents a privacy challenge when the LLM is augmented via tools or databases…

We review the use of differential privacy (DP) for privacy protection in machine learning (ML). We show that, driven by the aim of preserving the accuracy of the learned models, DP-based ML implementations are so loose that they do not…

Differential privacy (DP), provides a framework for provable privacy protection against arbitrary adversaries, while allowing the release of summary statistics and synthetic data. We address the problem of releasing a noisy real-valued…

Data holders are increasingly seeking to protect their user's privacy, whilst still maximizing their ability to produce machine models with high quality predictions. In this work, we empirically evaluate various implementations of…

Differential Privacy (DP) has become a gold standard in privacy-preserving data analysis. While it provides one of the most rigorous notions of privacy, there are many settings where its applicability is limited. Our main contribution is in…

The increasing demand for domain-specific and human-aligned Large Language Models (LLMs) has led to the widespread adoption of Supervised Fine-Tuning (SFT) techniques. SFT datasets often comprise valuable instruction-response pairs, making…

Large ASR models can inadvertently leak sensitive information, which can be mitigated by formal privacy measures like differential privacy (DP). However, traditional DP training is computationally expensive, and can hurt model performance.…

Differential privacy (DP) is a formal privacy framework that enables training machine learning (ML) models while protecting individuals' data. As pointed out by prior work, ML models are part of larger systems, which can lead to so-called…

In this paper, we aim to develop a scalable algorithm to preserve differential privacy (DP) in adversarial learning for deep neural networks (DNNs), with certified robustness to adversarial examples. By leveraging the sequential composition…

Differential privacy (DP) is a widely used approach for mitigating privacy risks when training machine learning models on sensitive data. DP mechanisms add noise during training to limit the risk of information leakage. The scale of the…

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…