English
Related papers

Related papers: Provably Confidential Language Modelling

200 papers

Deep learning models can achieve high inference accuracy by extracting rich knowledge from massive well-annotated data, but may pose the risk of data privacy leakage in practical deployment. In this paper, we present an effective…

Machine Learning · Computer Science 2024-09-20 Bochao Liu , Jianghu Lu , Pengju Wang , Junjie Zhang , Dan Zeng , Zhenxing Qian , Shiming Ge

As privacy gains traction in the NLP community, researchers have started adopting various approaches to privacy-preserving methods. One of the favorite privacy frameworks, differential privacy (DP), is perhaps the most compelling thanks to…

Computation and Language · Computer Science 2025-08-14 Ivan Habernal

Machine learning (ML) models can memorize training datasets. As a result, training ML models over private datasets can lead to the violation of individuals' privacy. Differential privacy (DP) is a rigorous privacy notion to preserve the…

Machine Learning · Computer Science 2024-02-13 Mohammad Hoseinpour , Milad Hoseinpour , Ali Aghagolzadeh

Recently, large language models (LLMs) have emerged as a notable field, attracting significant attention for its ability to automatically generate intelligent contents for various application domains. However, LLMs still suffer from…

Cryptography and Security · Computer Science 2024-04-29 Kongyang Chen , Zixin Wang , Bing Mi , Waixi Liu , Shaowei Wang , Xiaojun Ren , Jiaxing Shen

Privately generating synthetic data from a table is an important brick of a privacy-first world. We propose and investigate a simple approach of treating each row in a table as a sentence and training a language model with differential…

Machine Learning · Computer Science 2023-06-09 Alexandre Sablayrolles , Yue Wang , Brian Karrer

Large Language Models (LLMs) frequently memorize long sequences verbatim, often with serious legal and privacy implications. Much prior work has studied such verbatim memorization using observational data. To complement such work, we…

Computation and Language · Computer Science 2024-07-26 Jing Huang , Diyi Yang , Christopher Potts

The prevailing paradigm for training large reasoning models--combining Supervised Fine-Tuning (SFT) with Reinforcement Learning with Verifiable Rewards (RLVR)--is fundamentally constrained by its reliance on high-quality, human-annotated…

Machine Learning · Computer Science 2026-03-24 Yuanfu Wang , Zhixuan Liu , Xiangtian Li , Chaochao Lu , Chao Yang

Large language models (LLMs) are commonly adapted to downstream tasks through fine-tuning, but fine-tuning data often contains sensitive information that may be leaked by the resulting model. Differential privacy (DP) offers formal…

Machine Learning · Computer Science 2026-05-19 Haichao Sha , Zihao Wang , Yuncheng Wu , Hong Chen , Wei Dong

During the past decade, differential privacy has become the gold standard for protecting the privacy of individuals. However, verifying that a particular program provides differential privacy often remains a manual task to be completed by…

Programming Languages · Computer Science 2019-09-06 Joseph P. Near , David Darais , Chike Abuah , Tim Stevens , Pranav Gaddamadugu , Lun Wang , Neel Somani , Mu Zhang , Nikhil Sharma , Alex Shan , Dawn Song

We introduce the framework of "social learning" in the context of large language models (LLMs), whereby models share knowledge with each other in a privacy-aware manner using natural language. We present and evaluate two approaches for…

Machine Learning · Computer Science 2024-02-09 Amirkeivan Mohtashami , Florian Hartmann , Sian Gooding , Lukas Zilka , Matt Sharifi , Blaise Aguera y Arcas

News recommendation aims to display news articles to users based on their personal interest. Existing news recommendation methods rely on centralized storage of user behavior data for model training, which may lead to privacy concerns and…

Information Retrieval · Computer Science 2020-10-09 Tao Qi , Fangzhao Wu , Chuhan Wu , Yongfeng Huang , Xing Xie

The study of privacy-preserving Natural Language Processing (NLP) has gained rising attention in recent years. One promising avenue studies the integration of Differential Privacy in NLP, which has brought about innovative methods in a…

Computation and Language · Computer Science 2024-05-06 Stephen Meisenbacher , Maulik Chevli , Florian Matthes

Large Language models (LLMs) are trained on large amounts of data, which can include sensitive information that may compromise personal privacy. LLMs showed to memorize parts of the training data and emit those data verbatim when an…

Computation and Language · Computer Science 2023-05-03 Aly M. Kassem

This position paper investigates the integration of Differential Privacy (DP) in the training of Mixture of Experts (MoE) models within the field of natural language processing. As Large Language Models (LLMs) scale to billions of…

Cryptography and Security · Computer Science 2024-02-13 Pierre Tholoniat , Huseyin A. Inan , Janardhan Kulkarni , Robert Sim

Large language models (LLMs) exhibit remarkable capabilities in understanding and generating natural language. However, these models can inadvertently memorize private information, posing significant privacy risks. This study addresses the…

Computation and Language · Computer Science 2024-09-17 Zhenhua Liu , Tong Zhu , Chuanyuan Tan , Wenliang Chen

Spoken language understanding (SLU), one of the key enabling technologies for human-computer interaction in IoT devices, provides an easy-to-use user interface. Human speech can contain a lot of user-sensitive information, such as gender,…

Cryptography and Security · Computer Science 2024-03-26 Yinggui Wang , Wei Huang , Le Yang

Deep neural networks often use large, high-quality datasets to achieve high performance on many machine learning tasks. When training involves potentially sensitive data, this process can raise privacy concerns, as large models have been…

Machine Learning · Computer Science 2025-06-23 Felix Zhou , Samson Zhou , Vahab Mirrokni , Alessandro Epasto , Vincent Cohen-Addad

Machine learning models exhibit two seemingly contradictory phenomena: training data memorization, and various forms of forgetting. In memorization, models overfit specific training examples and become susceptible to privacy attacks. In…

While the flexible capabilities of large language models (LLMs) allow them to answer a range of queries based on existing learned knowledge, information retrieval to augment generation is an important tool to allow LLMs to answer questions…

Information Retrieval · Computer Science 2023-11-23 Guy Zyskind , Tobin South , Alex Pentland

Recently, pre-trained language representation flourishes as the mainstay of the natural language understanding community, e.g., BERT. These pre-trained language representations can create state-of-the-art results on a wide range of…

Machine Learning · Computer Science 2019-12-24 Fu-Ming Guo , Sijia Liu , Finlay S. Mungall , Xue Lin , Yanzhi Wang
‹ Prev 1 8 9 10 Next ›