Related papers: What Does it Mean for a Language Model to Preserve…
Pre-trained language models (PLMs) have demonstrated significant proficiency in solving a wide range of general natural language processing (NLP) tasks. Researchers have observed a direct correlation between the performance of these models…
In recent years, machine learning - particularly deep learning - has significantly impacted the field of information management. While several strategies have been proposed to restrict models from learning and memorizing sensitive…
Speech technology for communication, accessing information, and services has rapidly improved in quality. It is convenient and appealing because speech is the primary mode of communication for humans. Such technology, however, also presents…
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…
The privacy concerns associated with the use of Large Language Models (LLMs) have grown recently with the development of LLMs such as ChatGPT. Differential Privacy (DP) techniques are explored in existing work to mitigate their privacy…
Language models (LMs) are trained on collections of documents, written by individual human agents to achieve specific goals in an outside world. During training, LMs have access only to text of these documents, with no direct evidence of…
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…
This paper addresses the privacy and security concerns associated with deep neural language models, which serve as crucial components in various modern AI-based applications. These models are often used after being pre-trained and…
Large language models (LLMs) have been proven capable of memorizing their training data, which can be extracted through specifically designed prompts. As the scale of datasets continues to grow, privacy risks arising from memorization have…
Large language models trained on clinical text risk exposing sensitive patient information, yet differential privacy (DP) methods often severely degrade the diagnostic accuracy needed for deployment. Despite rapid progress in DP…
Differentially private training algorithms like DP-SGD protect sensitive training data by ensuring that trained models do not reveal private information. An alternative approach, which this paper studies, is to use a sensitive dataset to…
The last decade has seen a rise of Deep Learning with its applications ranging across diverse domains. But usually, the datasets used to drive these systems contain data which is highly confidential and sensitive. Though, Deep Learning…
Language models are capable of memorizing detailed patterns and information, leading to a double-edged effect: they achieve impressive modeling performance on downstream tasks with the stored knowledge but also raise significant privacy…
We study the problem of data release with privacy, where data is made available with privacy guarantees while keeping the usability of the data as high as possible --- this is important in health-care and other domains with sensitive data.…
Large Language Models (LLMs) memorize, and thus, among huge amounts of uncontrolled data, may memorize Personally Identifiable Information (PII), which should not be stored and, consequently, not leaked. In this paper, we introduce Private…
Differential privacy (DP) is applied when fine-tuning pre-trained large language models (LLMs) to limit leakage of training examples. While most DP research has focused on improving a model's privacy-utility tradeoff, some find that DP can…
We demonstrate that it is possible to train large recurrent language models with user-level differential privacy guarantees with only a negligible cost in predictive accuracy. Our work builds on recent advances in the training of deep…
Users interacting with large language models (LLMs) under their real identifiers often unknowingly risk disclosing private information. Automatically notifying users whether their queries leak privacy and which phrases leak what private…
Large language models (LLMs) have become the backbone of modern natural language processing but pose privacy concerns about leaking sensitive training data. Membership inference attacks (MIAs), which aim to infer whether a sample is…
We propose an alternate approach to quantifying how well language models learn natural language: we ask how well they match the statistical tendencies of natural language. To answer this question, we analyze whether text generated from…