Related papers: DPack: Efficiency-Oriented Privacy Budget Scheduli…
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…
Private machine learning introduces a trade-off between the privacy budget and training performance. Training convergence is substantially slower and extensive hyper parameter tuning is required. Consequently, efficient methods to conduct…
Artificial Intelligence (AI) models are vulnerable to information leakage of their training data, which can be highly sensitive, for example in medical imaging. Privacy Enhancing Technologies (PETs), such as Differential Privacy (DP), aim…
Differentially private (DP) decentralized Federated Learning (FL) allows local users to collaborate without sharing their data with a central server. However, accurately quantifying the privacy budget of private FL algorithms is challenging…
The standard definition of differential privacy (DP) ensures that a mechanism's output distribution on adjacent datasets is indistinguishable. However, real-world implementations of DP can, and often do, reveal information through their…
We give a fast algorithm to optimally compose privacy guarantees of differentially private (DP) algorithms to arbitrary accuracy. Our method is based on the notion of privacy loss random variables to quantify the privacy loss of DP…
Designing privacy-preserving machine learning algorithms has received great attention in recent years, especially in the setting when the data contains sensitive information. Differential privacy (DP) is a widely used mechanism for data…
Neural language models are known to have a high capacity for memorization of training samples. This may have serious privacy implications when training models on user content such as email correspondence. Differential privacy (DP), a…
Planning is one of the main approaches used to improve agents' working efficiency by making plans beforehand. However, during planning, agents face the risk of having their private information leaked. This paper proposes a novel strong…
In machine learning, privacy requirements at inference or deployment time often evolve due to changing policies, regulations, or user preferences. In this work, we aim to construct a magnitude of models to satisfy any target differential…
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…
Generative models trained with Differential Privacy (DP) can produce synthetic data while reducing privacy risks. However, navigating their privacy-utility tradeoffs makes finding the best models for specific settings/tasks challenging.…
Differential Privacy (DP) is a well-established framework to quantify privacy loss incurred by any algorithm. Traditional formulations impose a uniform privacy requirement for all users, which is often inconsistent with real-world scenarios…
In privacy-preserving machine learning, individual parties are reluctant to share their sensitive training data due to privacy concerns. Even the trained model parameters or prediction can pose serious privacy leakage. To address these…
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…
Language model alignment is crucial for ensuring that large language models (LLMs) align with human preferences, yet it often involves sensitive user data, raising significant privacy concerns. While prior work has integrated differential…
In-context learning (ICL) in Large Language Models (LLMs) has shown remarkable performance across various tasks without requiring fine-tuning. However, recent studies have highlighted the risk of private data leakage through the prompt in…
Security concerns in large-scale networked environments are becoming increasingly critical. To further improve the algorithm security from the design perspective of decentralized optimization algorithms, we introduce a new measure: Privacy…
Local differential privacy (LDP) can be adopted to anonymize richer user data attributes that will be input to sophisticated machine learning (ML) tasks. However, today's LDP approaches are largely task-agnostic and often lead to severe…
Distributed online learning is gaining increased traction due to its unique ability to process large-scale datasets and streaming data. To address the growing public awareness and concern on privacy protection, plenty of algorithms have…