paper-with-me

Papers

DP-NMT: Scalable Differentially-Private Machine Translation

2023-11-24 · Timour Igamberdiev, Doan Nam Long Vu, Felix Künnecke, Zhuo Yu, Jannik Holmer, Ivan Habernal

Neural machine translation (NMT) is a widely popular text generation task, yet there is a considerable research gap in the development of privacy-preserving NMT models, despite significant data privacy concerns for NMT systems. Differentially private stochastic gradient descent (DP-SGD) is a popular method for training machine learning models with concrete privacy guarantees; however, the implementation specifics of training a model with DP-SGD are not always clarified in existing models, with differing software libraries used and code bases not always being public, leading to reproducibility issues. To tackle this, we introduce DP-NMT, an open-source framework for carrying out research on privacy-preserving NMT with DP-SGD, bringing together numerous models, datasets, and evaluation metrics in one systematic software package. Our goal is to provide a platform for researchers to advance the development of privacy-preserving NMT systems, keeping the specific details of the DP-SGD algorithm transparent and intuitive to implement. We run a set of experiments on datasets from both general and privacy-related domains to demonstrate our framework in use. We make our framework publicly available and welcome feedback from the community.

📄 PDF Abstract BibTeX arXiv:2311.14465

Code (1)

trusthlt/dp-nmt 공식 구현 jax

Tasks

Machine TranslationNMTPrivacy PreservingText GenerationTranslation

Methods 이 논문이 사용한 방법론

SET Dynamic Sparse Training method where weight mask is updated randomly periodically

Similar Papers 제목 키워드 기반

Scalable and Provably Accurate Algorithms for Differentially Private Distributed Decision Tree Learning

2020-12-19 · Kaiwen Wang, Travis Dick, Maria-Florina Balcan

This paper introduces the first provably accurate algorithms for differentially private, top-down decision tree learning in the distributed setting (Balcan et al., 2012). We propose DP-TopDown, a general privacy preservi…

Privacy Preserving

Differentially Private Algorithms for Empirical Machine Learning

2014-11-20 · Ben Stoddard, Yan Chen, Ashwin Machanavajjhala

An important use of private data is to build machine learning classifiers. While there is a burgeoning literature on differentially private classification algorithms, we find that they are not practical in real applicati…

BIG-bench Machine LearningGeneral Classification

Differentially Private Synthetic Data: Applied Evaluations and Enhancements

2020-11-11 · Lucas Rosenblatt, Xiaoyan Liu, Samira Pouyanfar, Eduardo de Leon 외

Machine learning practitioners frequently seek to leverage the most informative available data, without violating the data owner's privacy, when building predictive models. Differentially private data synthesis protects …

BIG-bench Machine Learning

Rethinking Benchmarks for Differentially Private Image Classification

2026-01-23 · Sabrina Mokhtari, Sara Kodeiri, Shubhankar Mohapatra, Florian Tramèr 외 arxiv

We revisit benchmarks for differentially private image classification. We suggest a comprehensive set of benchmarks, allowing researchers to evaluate techniques for differentially private machine learning in a variety of…

Image Classification

Revisiting ML Training under Fully Homomorphic Encryption: Convergence Guarantees, Differential Privacy, and Efficient Algorithms

2026-05-27 · Yvonne Zhou, Mingyu Liang, Ivan Brugere, Danial Dervovic 외 arxiv

We present the first theoretical convergence analysis of machine learning training under fully homomorphic encryption (FHE), combined with a differentially private (DP) training algorithm tailored to encrypted computatio…

Computational Efficiency