相关论文: Privacy Enhanced PEFT: Tensor Train Decomposition …

Privacy-preserving training on sensitive data commonly relies on differentially private stochastic optimization with gradient clipping and Gaussian noise. The clipping threshold is a critical control knob: if set too small, systematic…

Federated learning is distributed model training across several clients without disclosing raw data. Despite advancements in data privacy, risks still remain. Differential Privacy (DP) is a technique to protect sensitive data by adding…

Parameter-efficient fine-tuning (PEFT) methods reduce the computational costs of updating deep learning models by minimizing the number of additional parameters used to adapt a model to a down- stream task. While extensively researched in…

Large convolutional neural networks (CNN) can be difficult to train in the differentially private (DP) regime, since the optimization algorithms require a computationally expensive operation, known as the per-sample gradient clipping. We…

With the emerging trend in generative models and convenient public access to diffusion models pre-trained on large datasets, users can fine-tune these models to generate images of personal faces or items in new contexts described by natural…

Large language models have repeatedly shown outstanding performance across diverse applications. However, deploying these models can inadvertently risk user privacy. The significant memory demands during training pose a major challenge in…

We train language models (LMs) with federated learning (FL) and differential privacy (DP) in the Google Keyboard (Gboard). We apply the DP-Follow-the-Regularized-Leader (DP-FTRL)~\citep{kairouz21b} algorithm to achieve meaningfully formal…

Leveraging transfer learning has recently been shown to be an effective strategy for training large models with Differential Privacy (DP). Moreover, somewhat surprisingly, recent works have found that privately training just the last layer…

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…

Differentially private stochastic gradient descent (DP-SGD) allows models to be trained in a privacy-preserving manner, but has proven difficult to scale to the era of foundation models. We introduce DP-ZO, a private fine-tuning framework…

This article presents DDP-SA, a scalable privacy-preserving federated learning framework that jointly leverages client-side local differential privacy (LDP) and full-threshold additive secret sharing (ASS) for secure aggregation. Unlike…

Federated learning (FL) enables collaborative model training across distributed clients without sharing raw data, making it a promising approach for privacy-preserving machine learning. However, ensuring differential privacy (DP) in FL…

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,…

The state-of-the-art for training on-device language models for mobile keyboard applications combines federated learning (FL) with differential privacy (DP) via the DP-Follow-the-Regularized-Leader (DP-FTRL) algorithm. Two variants of…

In real-world applications, domain data often contains identifiable or sensitive attributes, is subject to strict regulations (e.g., HIPAA, GDPR), and requires explicit data feature engineering for interpretability and transparency.…

Low-Rank Adaptation (LoRA) has emerged as one of the most widely used parameter-efficient fine-tuning (PEFT) methods for adapting large language models (LLMs) to downstream tasks. While highly effective in single-task settings, it struggles…

Reinforcement learning (RL) algorithms can be used to provide personalized services, which rely on users' private and sensitive data. To protect the users' privacy, privacy-preserving RL algorithms are in demand. In this paper, we study RL…

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…

Train machine learning models on sensitive user data has raised increasing privacy concerns in many areas. Federated learning is a popular approach for privacy protection that collects the local gradient information instead of real data.…

We address the challenge of sample efficiency in differentially private fine-tuning of large language models (LLMs) using DP-SGD. While DP-SGD provides strong privacy guarantees, the added noise significantly increases the entropy of…