English
Related papers

Related papers: DP-Forward: Fine-tuning and Inference on Language …

200 papers

Differentially Private (DP) learning has seen limited success for building large deep learning models of text, and straightforward attempts at applying Differentially Private Stochastic Gradient Descent (DP-SGD) to NLP tasks have resulted…

Machine Learning · Computer Science 2022-11-11 Xuechen Li , Florian Tramèr , Percy Liang , Tatsunori Hashimoto

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,…

Machine Learning · Statistics 2024-01-02 Tim Dockhorn , Tianshi Cao , Arash Vahdat , Karsten Kreis

Differentially private SGD (DP-SGD) is one of the most popular methods for solving differentially private empirical risk minimization (ERM). Due to its noisy perturbation on each gradient update, the error rate of DP-SGD scales with the…

Machine Learning · Computer Science 2021-04-27 Yingxue Zhou , Zhiwei Steven Wu , Arindam Banerjee

Differentially Private Stochastic Gradient Descent (DP-SGD) is the dominant paradigm for private training, but its fundamental limitations under worst-case adversarial privacy definitions remain poorly understood. We analyze DP-SGD in the…

Machine Learning · Computer Science 2026-04-17 Murat Bilgehan Ertan , Marten van Dijk

Learning often involves sensitive data and as such, privacy preserving extensions to Stochastic Gradient Descent (SGD) and other machine learning algorithms have been developed using the definitions of Differential Privacy (DP). In…

Machine Learning · Computer Science 2021-10-14 Friedrich Dörmann , Osvald Frisk , Lars Nørvang Andersen , Christian Fischer Pedersen

Fine-tuning large language models on downstream tasks is crucial for realizing their cross-domain potential but often relies on sensitive data, raising privacy concerns. Differential privacy (DP) offers rigorous privacy guarantees and has…

Machine Learning · Computer Science 2026-01-19 Lele Zheng , Xiang Wang , Tao Zhang , Yang Cao , Ke Cheng , Yulong Shen

Differentially private stochastic gradient descent (DP-SGD) offers the promise of training deep learning models while mitigating many privacy risks. However, there is currently a large accuracy gap between DP-SGD and normal SGD training.…

Machine Learning · Computer Science 2026-03-24 Xin Gu , Yingtai Xiao , Guanlin He , Jiamu Bai , Daniel Kifer , Kiwan Maeng

In the domain of deep learning, the challenge of protecting sensitive data while maintaining model utility is significant. Traditional Differential Privacy (DP) techniques such as Differentially Private Stochastic Gradient Descent (DP-SGD)…

Machine Learning · Computer Science 2024-11-06 Tao Huang , Qingyu Huang , Xin Shi , Jiayang Meng , Guolong Zheng , Xu Yang , Xun Yi

Differentially Private Stochastic Gradient Descent (DPSGD) is widely used to train deep neural networks with formal privacy guarantees. However, the addition of differential privacy (DP) often degrades model accuracy by introducing both…

Machine Learning · Computer Science 2025-11-13 Xincheng Xu , Thilina Ranbaduge , Qing Wang , Thierry Rakotoarivelo , David Smith

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.…

Cryptography and Security · Computer Science 2022-04-28 Zhigang Lu , Hassan Jameel Asghar , Mohamed Ali Kaafar , Darren Webb , Peter Dickinson

Differentially private stochastic gradient descent (DP-SGD) is the canonical approach to private deep learning. While the current privacy analysis of DP-SGD is known to be tight in some settings, several empirical results suggest that…

Machine Learning · Computer Science 2024-07-17 Anvith Thudi , Hengrui Jia , Casey Meehan , Ilia Shumailov , Nicolas Papernot

Deep learning models leak significant amounts of information about their training datasets. Previous work has investigated training models with differential privacy (DP) guarantees through adding DP noise to the gradients. However, such…

Machine Learning · Computer Science 2020-07-23 Milad Nasr , Reza Shokri , Amir houmansadr

Machine learning models trained with differentially-private (DP) algorithms such as DP-SGD enjoy resilience against a wide range of privacy attacks. Although it is possible to derive bounds for some attacks based solely on an…

Cryptography and Security · Computer Science 2024-02-23 Giovanni Cherubin , Boris Köpf , Andrew Paverd , Shruti Tople , Lukas Wutschitz , Santiago Zanella-Béguelin

Differentially private stochastic gradient descent (DP-SGD) is the workhorse algorithm for recent advances in private deep learning. It provides a single privacy guarantee to all datapoints in the dataset. We propose output-specific…

Machine Learning · Computer Science 2024-07-26 Da Yu , Gautam Kamath , Janardhan Kulkarni , Tie-Yan Liu , Jian Yin , Huishuai Zhang

Large language models (LLMs) are trained on vast datasets that may contain sensitive information. Differential privacy (DP), the de facto standard for formal privacy guarantees, provides a principled framework for training LLMs with…

Machine Learning · Computer Science 2026-05-26 Enayat Ullah , Sai Aparna Aketi , Devansh Gupta , Huanyu Zhang , Meisam Razaviyayn

Differentially Private Stochastic Gradient Descent with Gradient Clipping (DPSGD-GC) is a powerful tool for training deep learning models using sensitive data, providing both a solid theoretical privacy guarantee and high efficiency.…

Machine Learning · Computer Science 2024-04-18 Xinwei Zhang , Zhiqi Bu , Zhiwei Steven Wu , Mingyi Hong

In Embedding-as-an-Interface (EaaI) settings, pre-trained models are queried for Intermediate Representations (IRs). The distributional properties of IRs can leak training-set membership signals, enabling Membership Inference Attacks (MIAs)…

Machine Learning · Computer Science 2026-05-12 Jiayang Meng , Tao Huang , Chen Hou , Guolong Zheng , Hong Chen

Machine learning models are known to memorize private data to reduce their training loss, which can be inadvertently exploited by privacy attacks such as model inversion and membership inference. To protect against these attacks,…

Machine Learning · Computer Science 2023-11-30 Jie Fu , Qingqing Ye , Haibo Hu , Zhili Chen , Lulu Wang , Kuncan Wang , Xun Ran

Differential Privacy (DP) provides a formal framework for training machine learning models with individual example level privacy. In the field of deep learning, Differentially Private Stochastic Gradient Descent (DP-SGD) has emerged as a…

Machine Learning · Computer Science 2022-05-24 Harsh Mehta , Abhradeep Thakurta , Alexey Kurakin , Ashok Cutkosky

Differentially Private Stochastic Gradient Descent (DP-SGD) and its variants have been proposed to ensure rigorous privacy for fine-tuning large-scale pre-trained language models. However, they rely heavily on the Gaussian mechanism, which…

Cryptography and Security · Computer Science 2024-05-30 Qin Yang , Meisam Mohammad , Han Wang , Ali Payani , Ashish Kundu , Kai Shu , Yan Yan , Yuan Hong