相关论文: SA-ADP: Sensitivity-Aware Adaptive Differential Pr…

Applying differential privacy (DP) by means of the DP-SGD algorithm to protect individual data points during training is becoming increasingly popular in NLP. However, the choice of granularity at which DP is applied is often neglected. For…

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…

Unsupervised pre-training is a common step in developing computer vision models and large language models. In this setting, the absence of labels requires the use of similarity-based loss functions, such as contrastive loss, that favor…

The integration of Differential Privacy (DP) with diffusion models (DMs) presents a promising yet challenging frontier, particularly due to the substantial memorization capabilities of DMs that pose significant privacy risks. Differential…

We demonstrate that it is possible to train large recurrent language models with user-level differential privacy guarantees with only a negligible cost in predictive accuracy. Our work builds on recent advances in the training of deep…

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)…

Differential privacy (DP) has been applied in deep learning for preserving privacy of the underlying training sets. Existing DP practice falls into three categories - objective perturbation, gradient perturbation and output perturbation.…

Fall detection is a critical task in healthcare, particularly for elderly people. Timely fall detection and treatment can prevent severe injuries. Sensor-based activity data can be used to detect fall. However, this data are highly…

Differential privacy (DP) is crucial for safeguarding sensitive client information in federated learning (FL), yet traditional DP-FL methods rely predominantly on fixed gradient clipping thresholds. Such static clipping neglects significant…

As data-driven technologies advance swiftly, maintaining strong privacy measures becomes progressively difficult. Conventional $(\epsilon, \delta)$-differential privacy, while prevalent, exhibits limited adaptability for many applications.…

Differentially private (DP) mechanisms face the challenge of providing accurate results while protecting their inputs: the privacy-utility trade-off. A simple but powerful technique for DP adds noise to sensitivity-bounded query outputs to…

Differential privacy (DP) is one data protection avenue to safeguard user information used for training deep models by imposing noisy distortion on privacy data. Such a noise perturbation often results in a severe performance degradation in…

Nowadays, differential privacy (DP) has become a well-accepted standard for privacy protection, and deep neural networks (DNN) have been immensely successful in machine learning. The combination of these two techniques, i.e., deep learning…

Federated Learning (FL) enables collaborative model training without direct data sharing, yet it remains vulnerable to privacy attacks such as model inversion and membership inference. Existing differential privacy (DP) solutions for FL…

Federated learning (FL) enhances privacy by keeping user data on local devices. However, emerging attacks have demonstrated that the updates shared by users during training can reveal significant information about their data. This has…

A well-known algorithm in privacy-preserving ML is differentially private stochastic gradient descent (DP-SGD). While this algorithm has been evaluated on text and image data, it has not been previously applied to ads data, which are…

Language modeling is a keystone task in natural language processing. When training a language model on sensitive information, differential privacy (DP) allows us to quantify the degree to which our private data is protected. However,…

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]…

Fine-tuning large language models (LLMs) for specific tasks introduces privacy risks, as models may inadvertently memorise and leak sensitive training data. While Differential Privacy (DP) offers a solution to mitigate these risks, it…

Differential privacy (DP) techniques can be applied to the federated learning model to protect data privacy against inference attacks to communication among the learning agents. The DP techniques, however, hinder achieving a greater…