English
Related papers

Related papers: Efficient Differentially Private Fine-Tuning of LL…

200 papers

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

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…

Machine Learning · Computer Science 2025-02-03 Xinyu Tang , Ashwinee Panda , Milad Nasr , Saeed Mahloujifar , Prateek Mittal

Prior work on differential privacy analysis of randomized SGD algorithms relies on composition theorems, where the implicit (unrealistic) assumption is that the internal state of the iterative algorithm is revealed to the adversary. As a…

Machine Learning · Statistics 2022-10-18 Jiayuan Ye , Reza Shokri

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

In this paper, we consider efficient differentially private empirical risk minimization from the viewpoint of optimization algorithms. For strongly convex and smooth objectives, we prove that gradient descent with output perturbation not…

Machine Learning · Computer Science 2017-05-25 Jiaqi Zhang , Kai Zheng , Wenlong Mou , Liwei Wang

We propose a reparametrization scheme to address the challenges of applying differentially private SGD on large neural networks, which are 1) the huge memory cost of storing individual gradients, 2) the added noise suffering notorious…

Machine Learning · Computer Science 2021-11-05 Da Yu , Huishuai Zhang , Wei Chen , Jian Yin , Tie-Yan Liu

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…

Cryptography and Security · Computer Science 2026-03-31 Payel Bhattacharjee , Fengwei Tian , Geoffrey D. Rubin , Joseph Y. Lo , Nirav Merchant , Heidi Hanson , John Gounley , Ravi Tandon

Differential privacy (DP) provides a formal privacy guarantee that prevents adversaries with access to machine learning models from extracting information about individual training points. Differentially private stochastic gradient descent…

Cryptography and Security · Computer Science 2022-12-15 Jie Fu , Zhili Chen , XinPeng Ling

Federated Learning (FL) allows for the training of Machine Learning models in a collaborative manner without the need to share sensitive data. However, it remains vulnerable to Gradient Leakage Attacks (GLAs), which can reveal private…

Machine Learning · Computer Science 2025-10-29 Miguel Fernandez-de-Retana , Unai Zulaika , Rubén Sánchez-Corcuera , Aitor Almeida

By ensuring differential privacy in the learning algorithms, one can rigorously mitigate the risk of large models memorizing sensitive training data. In this paper, we study two algorithms for this purpose, i.e., DP-SGD and DP-NSGD, which…

Machine Learning · Computer Science 2022-06-28 Xiaodong Yang , Huishuai Zhang , Wei Chen , Tie-Yan Liu

Deep learning models are increasingly popular in many machine learning applications where the training data may contain sensitive information. To provide formal and rigorous privacy guarantee, many learning systems now incorporate…

Machine Learning · Computer Science 2021-03-19 Xiangyi Chen , Zhiwei Steven Wu , Mingyi Hong

The hidden state threat model of differential privacy (DP) assumes that the adversary has access only to the final trained machine learning (ML) model, without seeing intermediate states during training. However, the current privacy…

Machine Learning · Computer Science 2025-05-27 Rob Romijnders , Antti Koskela

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…

Machine Learning · Computer Science 2024-11-26 Olivia Ma , Jonathan Passerat-Palmbach , Dmitrii Usynin

Differential privacy (DP) protects sensitive data during neural network training, but standard methods like DP-Adam suffer from high memory overhead due to per-sample gradient clipping, limiting scalability. We introduce DP-GRAPE (Gradient…

Machine Learning · Computer Science 2026-05-19 Alex Mulrooney , Devansh Gupta , James Flemings , Huanyu Zhang , Murali Annavaram , Meisam Razaviyayn , Xinwei Zhang

We consider three different variants of differential privacy (DP), namely approximate DP, R\'enyi DP (RDP), and hypothesis test DP. In the first part, we develop a machinery for optimally relating approximate DP to RDP based on the joint…

Information Theory · Computer Science 2021-01-26 Shahab Asoodeh , Jiachun Liao , Flavio P. Calmon , Oliver Kosut , Lalitha Sankar

Differentially private learning is essential for training models on sensitive data, but empirical studies consistently show that it can degrade performance, introduce fairness issues like disparate impact, and reduce adversarial robustness.…

Machine Learning · Computer Science 2026-04-21 Ruichen Xu , Kexin Chen

Differential privacy (DP) is a privacy-preserving paradigm that protects the training data when training deep learning models. Critically, the performance of models is determined by the training hyperparameters, especially those of the…

Machine Learning · Computer Science 2025-03-04 Zhiqi Bu , Ruixuan Liu

We present backpropagation clipping, a novel variant of differentially private stochastic gradient descent (DP-SGD) for privacy-preserving deep learning. Our approach clips each trainable layer's inputs (during the forward pass) and its…

Machine Learning · Computer Science 2022-02-21 Timothy Stevens , Ivoline C. Ngong , David Darais , Calvin Hirsch , David Slater , Joseph P. Near

Differentially private (DP) training preserves the data privacy usually at the cost of slower convergence (and thus lower accuracy), as well as more severe mis-calibration than its non-private counterpart. To analyze the convergence of DP…

Machine Learning · Computer Science 2023-06-21 Zhiqi Bu , Hua Wang , Zongyu Dai , Qi Long

Recently, due to the popularity of deep neural networks and other methods whose training typically relies on the optimization of an objective function, and due to concerns for data privacy, there is a lot of interest in differentially…

Machine Learning · Computer Science 2025-02-12 Antoine Barczewski , Jan Ramon
‹ Prev 1 3 4 5 6 7 10 Next ›