Related papers: Provably Confidential Language Modelling
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…
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…
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…
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…
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…
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…
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…
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…
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…
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…
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…
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…
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…
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…
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…
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,…
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 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…
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…