Related papers: Accuracy Improvement in Differentially Private Log…

Federated learning (FL) that enables edge devices to collaboratively learn a shared model while keeping their training data locally has received great attention recently and can protect privacy in comparison with the traditional centralized…

Large language models (LLMs) have significantly transformed natural language understanding and generation, but they raise privacy concerns due to potential exposure of sensitive information. Studies have highlighted the risk of information…

The privacy concerns associated with the use of Large Language Models (LLMs) have grown recently with the development of LLMs such as ChatGPT. Differential Privacy (DP) techniques are explored in existing work to mitigate their privacy…

Differential privacy (DP) is an essential technique for privacy-preserving. It was found that a large model trained for privacy preserving performs worse than a smaller model (e.g. ResNet50 performs worse than ResNet18). To better…

Deep learning techniques have achieved remarkable performance in wide-ranging tasks. However, when trained on privacy-sensitive datasets, the model parameters may expose private information in training data. Prior attempts for…

Large Language Models (LLMs) are increasingly adopted across domains such as education, healthcare, and finance. In healthcare, LLMs support tasks including disease diagnosis, abnormality classification, and clinical decision-making. Among…

Modern Integrated Development Environments (IDEs) increasingly leverage Large Language Models (LLMs) to provide advanced features like code autocomplete. While powerful, training these models on user-written code introduces significant…

The increasing deployment of Machine Learning (ML) models in sensitive domains motivates the need for robust, practical privacy assessment tools. PrivacyGuard is a comprehensive tool for empirical differential privacy (DP) analysis,…

We study the inherent trade-offs in minimizing privacy risks and maximizing utility, while maintaining high computational efficiency, when fine-tuning large language models (LLMs). A number of recent works in privacy research have attempted…

Predictive machine learning models are becoming increasingly deployed in high-stakes contexts involving sensitive personal data; in these contexts, there is a trade-off between model explainability and data privacy. In this work, we push…

Quantum machine learning (QML) can complement the growing trend of using learned models for a myriad of classification tasks, from image recognition to natural speech processing. A quantum advantage arises due to the intractability of…

We investigate practical and scalable algorithms for training large language models (LLMs) with user-level differential privacy (DP) in order to provably safeguard all the examples contributed by each user. We study two variants of DP-SGD…

As sufficient data are not always publically accessible for model training, researchers exploit limited data with advanced learning algorithms or expand the dataset via data augmentation (DA). Conducting DA in private domain requires…

Approximate machine unlearning aims to remove the effect of specific data from trained models to ensure individuals' privacy. Existing methods focus on the removed records and assume the retained ones are unaffected. However, recent studies…

Differentially Private Stochastic Gradients Descent (DP-SGD) is a prominent paradigm for preserving privacy in deep learning. It ensures privacy by perturbing gradients with random noise calibrated to their entire norm at each training…

While being deployed in many critical applications as core components, machine learning (ML) models are vulnerable to various security and privacy attacks. One major privacy attack in this domain is membership inference, where an adversary…

When applying differential privacy to sensitive data, we can often improve performance using external information such as other sensitive data, public data, or human priors. We propose to use the learning-augmented algorithms (or algorithms…

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.…

A major challenge in applying differential privacy to training deep neural network models is scalability.The widely-used training algorithm, differentially private stochastic gradient descent (DP-SGD), struggles with training…

The rise of connected personal devices together with privacy concerns call for machine learning algorithms capable of leveraging the data of a large number of agents to learn personalized models under strong privacy requirements. In this…