English
Related papers

Related papers: Data Efficient Subset Training with Differential P…

200 papers

In order to both learn and protect sensitive training data, there has been a growing interest in privacy preserving machine learning methods. Differential privacy has emerged as an important measure of privacy. We are interested in the…

Cryptography and Security · Computer Science 2025-02-11 Antoine Barczewski , Amal Mawass , Jan Ramon

Federated learning enables collaborative model training across distributed clients while preserving data privacy. However, in practical deployments, device heterogeneity, non-independent, and identically distributed (Non-IID) data often…

Artificial Intelligence · Computer Science 2026-02-20 Jin Wang , Hui Ma , Fei Xing , Ming Yan

Recent papers have shown that large pre-trained language models (LLMs) such as BERT, GPT-2 can be fine-tuned on private data to achieve performance comparable to non-private models for many downstream Natural Language Processing (NLP) tasks…

Machine Learning · Computer Science 2022-06-07 Fatemehsadat Mireshghallah , Arturs Backurs , Huseyin A Inan , Lukas Wutschitz , Janardhan Kulkarni

The performance of federated learning systems is bottlenecked by communication costs and training variance. The communication overhead problem is usually addressed by three communication-reduction techniques, namely, model compression,…

Machine Learning · Computer Science 2021-02-01 Nima Mohammadi , Jianan Bai , Qiang Fan , Yifei Song , Yang Yi , Lingjia Liu

Differentially private gradient descent (DP-GD) is a popular algorithm to train deep learning models with provable guarantees on the privacy of the training data. In the last decade, the problem of understanding its performance cost with…

Machine Learning · Statistics 2025-05-29 Simone Bombari , Marco Mondelli

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…

Fine-tuning large language models (LLMs) has become an essential strategy for adapting them to specialized tasks; however, this process introduces significant privacy challenges, as sensitive training data may be inadvertently memorized and…

Cryptography and Security · Computer Science 2025-05-02 Hao Du , Shang Liu , Yang Cao

Machine learning models can be used for pattern recognition in medical data in order to improve patient outcomes, such as the prediction of in-hospital mortality. Deep learning models, in particular, require large amounts of data for model…

Machine Learning · Computer Science 2019-12-03 Pulkit Sharma , Farah E Shamout , David A Clifton

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

In the privacy-utility tradeoff of a model trained on benchmark language and vision tasks, remarkable improvements have been widely reported with the use of pretraining on publicly available data. This is in part due to the benefits of…

Machine Learning · Computer Science 2023-02-21 Arun Ganesh , Mahdi Haghifam , Milad Nasr , Sewoong Oh , Thomas Steinke , Om Thakkar , Abhradeep Thakurta , Lun Wang

Recent advances in deep learning have drastically improved performance on many Natural Language Understanding (NLU) tasks. However, the data used to train NLU models may contain private information such as addresses or phone numbers,…

Computation and Language · Computer Science 2022-03-03 Christophe Dupuy , Radhika Arava , Rahul Gupta , Anna Rumshisky

Tuning the hyperparameters of differentially private (DP) machine learning (ML) algorithms often requires use of sensitive data and this may leak private information via hyperparameter values. Recently, Papernot and Steinke (2022) proposed…

Machine Learning · Computer Science 2024-02-14 Antti Koskela , Tejas Kulkarni

A key factor in developing high performing machine learning models is the availability of sufficiently large datasets. This work is motivated by applications arising in Software as a Service (SaaS) companies where there exist numerous…

Machine Learning · Computer Science 2018-12-05 Sophia Collet , Robert Dadashi , Zahi N. Karam , Chang Liu , Parinaz Sobhani , Yevgeniy Vahlis , Ji Chao Zhang

Bias in data can have unintended consequences that propagate to the design, development, and deployment of machine learning models. In the financial services sector, this can result in discrimination from certain financial instruments and…

Cryptography and Security · Computer Science 2019-11-12 Reginald Bryant , Celia Cintas , Isaac Wambugu , Andrew Kinai , Komminist Weldemariam

Nowadays, the development of information technology is growing rapidly. In the big data era, the privacy of personal information has been more pronounced. The major challenge is to find a way to guarantee that sensitive personal information…

Machine Learning · Computer Science 2022-10-17 Mengde Han , Tianqing Zhu , Wanlei Zhou

Differential privacy (DP) ensures that training a machine learning model does not leak private data. In practice, we may have access to auxiliary public data that is free of privacy concerns. In this work, we assume access to a given amount…

Machine Learning · Computer Science 2024-09-11 Andrew Lowy , Zeman Li , Tianjian Huang , Meisam Razaviyayn

The Gradient Boosting Decision Tree (GBDT) is a popular machine learning model for various tasks in recent years. In this paper, we study how to improve model accuracy of GBDT while preserving the strong guarantee of differential privacy.…

Machine Learning · Computer Science 2022-10-11 Qinbin Li , Zhaomin Wu , Zeyi Wen , Bingsheng He

Algorithms such as Differentially Private SGD enable training machine learning models with formal privacy guarantees. However, there is a discrepancy between the protection that such algorithms guarantee in theory and the protection they…

Training large neural networks with meaningful/usable differential privacy security guarantees is a demanding challenge. In this paper, we tackle this problem by revisiting the two key operations in Differentially Private Stochastic…

Machine Learning · Computer Science 2022-10-11 Hanshen Xiao , Jun Wan , Srinivas Devadas

A successful machine learning (ML) algorithm often relies on a large amount of high-quality data to train well-performed models. Supervised learning approaches, such as deep learning techniques, generate high-quality ML functions for…

Machine Learning · Computer Science 2022-11-15 Thilina Ranbaduge , Ming Ding
‹ Prev 1 3 4 5 6 7 10 Next ›