English
Related papers

Related papers: Sample-Efficient Differentially Private Fine-Tunin…

200 papers

Gradient clipping is a fundamental tool in Deep Learning, improving the high-probability convergence of stochastic first-order methods like SGD, AdaGrad, and Adam under heavy-tailed noise, which is common in training large language models.…

Machine Learning · Computer Science 2025-09-30 Saleh Vatan Khah , Savelii Chezhegov , Shahrokh Farahmand , Samuel Horváth , Eduard Gorbunov

Deep learning models have been extensively adopted in various regions due to their ability to represent hierarchical features, which highly rely on the training set and procedures. Thus, protecting the training process and deep learning…

Cryptography and Security · Computer Science 2025-03-12 Haodi Wang , Tangyu Jiang , Yu Guo , Chengjun Cai , Cong Wang , Xiaohua Jia

Training deep learning models with differential privacy (DP) results in a degradation of performance. The training dynamics of models with DP show a significant difference from standard training, whereas understanding the geometric…

Machine Learning · Computer Science 2023-06-12 Jinseong Park , Hoki Kim , Yujin Choi , Jaewook Lee

Decentralized min-max optimization allows multi-agent systems to collaboratively solve global min-max optimization problems by facilitating the exchange of model updates among neighboring agents, eliminating the need for a central server.…

Machine Learning · Computer Science 2025-08-12 Yueyang Quan , Chang Wang , Shengjie Zhai , Minghong Fang , Zhuqing Liu

Differential privacy (DP) has become a prevalent privacy model in a wide range of machine learning tasks, especially after the debut of DP-SGD. However, DP-SGD, which directly perturbs gradients in the training iterations, fails to mitigate…

Machine Learning · Computer Science 2025-04-09 Jiawei Duan , Haibo Hu , Qingqing Ye , Xinyue Sun

Nowadays, differential privacy (DP) has become a well-accepted standard for privacy protection, and deep neural networks (DNN) have been immensely successful in machine learning. The combination of these two techniques, i.e., deep learning…

Cryptography and Security · Computer Science 2024-08-02 Jianxin Wei , Ergute Bao , Xiaokui Xiao , Yin Yang

A major challenge for machine learning is increasing the availability of data while respecting the privacy of individuals. Here we combine the provable privacy guarantees of the differential privacy framework with the flexibility of…

Machine Learning · Statistics 2019-01-18 Michael Thomas Smith , Max Zwiessele , Neil D. Lawrence

Despite advances in the use of large language models (LLMs) in downstream tasks, their ability to memorize information has raised privacy concerns. Therefore, protecting personally identifiable information (PII) during LLM training remains…

Machine Learning · Computer Science 2025-12-02 Stella Etuk , Ashraf Matrawy

Stochastic optimization is a pivotal enabler in modern machine learning, producing effective models for various tasks. However, several existing works have shown that model parameters and gradient information are susceptible to privacy…

Machine Learning · Computer Science 2025-09-15 Zhanhong Jiang , Md Zahid Hasan , Nastaran Saadati , Aditya Balu , Chao Liu , Soumik Sarkar

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

Differentially Private Stochastic Gradient Descent (DP-SGD) is widely used to protect training data in machine learning. Its privacy guarantee is commonly analyzed through a security game in which an adversary infers whether a target record…

Cryptography and Security · Computer Science 2026-05-18 Wenhao Wang , Shujie Cui , Hui Cui , Xingliang Yuan

We address the challenge of ensuring differential privacy (DP) guarantees in training deep retrieval systems. Training these systems often involves the use of contrastive-style losses, which are typically non-per-example decomposable,…

Computation and Language · Computer Science 2024-05-24 Aldo Gael Carranza , Rezsa Farahani , Natalia Ponomareva , Alex Kurakin , Matthew Jagielski , Milad Nasr

While significant progress has been made separately on analytics systems for scalable stochastic gradient descent (SGD) and private SGD, none of the major scalable analytics frameworks have incorporated differentially private SGD. There are…

Machine Learning · Computer Science 2017-03-24 Xi Wu , Fengan Li , Arun Kumar , Kamalika Chaudhuri , Somesh Jha , Jeffrey F. Naughton

Ensuring the privacy of Large Language Models (LLMs) is becoming increasingly important. The most widely adopted technique to accomplish this is DP-SGD, which trains a model to guarantee Differential Privacy (DP). However, DP-SGD…

Cryptography and Security · Computer Science 2024-04-30 James Flemings , Meisam Razaviyayn , Murali Annavaram

Many problems in trustworthy ML can be formulated as minimization of the model error under constraints on the prediction rates of the model for suitably-chosen marginals, including most group fairness constraints (demographic parity,…

Machine Learning · Computer Science 2025-05-30 Mohammad Yaghini , Tudor Cebere , Michael Menart , Aurélien Bellet , Nicolas Papernot

The Noisy-SGD algorithm is widely used for privately training machine learning models. Traditional privacy analyses of this algorithm assume that the internal state is publicly revealed, resulting in privacy loss bounds that increase…

Machine Learning · Computer Science 2023-05-18 Shahab Asoodeh , Mario Diaz

Nowadays, owners and developers of deep learning models must consider stringent privacy-preservation rules of their training data, usually crowd-sourced and retaining sensitive information. The most widely adopted method to enforce privacy…

Machine Learning · Computer Science 2022-09-08 Eugenio Lomurno , Matteo matteucci

The widespread practice of fine-tuning large language models (LLMs) on domain-specific data faces two major challenges in memory and privacy. First, as the size of LLMs continues to grow, the memory demands of gradient-based training…

Machine Learning · Computer Science 2024-06-07 Liang Zhang , Bingcong Li , Kiran Koshy Thekumparampil , Sewoong Oh , Niao He

Differentially Private Stochastic Gradient Descent (DP-SGD) is a key method for applying privacy in the training of deep learning models. It applies isotropic Gaussian noise to gradients during training, which can perturb these gradients in…

Machine Learning · Computer Science 2023-11-28 Pedro Faustini , Natasha Fernandes , Shakila Tonni , Annabelle McIver , Mark Dras

Differentially Private Stochastic Gradient Descent (DP-SGD) limits the amount of private information deep learning models can memorize during training. This is achieved by clipping and adding noise to the model's gradients, and thus…

Computer Vision and Pattern Recognition · Computer Science 2023-06-22 Florian A. Hölzl , Daniel Rueckert , Georgios Kaissis
‹ Prev 1 3 4 5 6 7 10 Next ›