Related papers: ER-AE: Differentially Private Text Generation for …

Personalized text generation requires models not only to produce coherent text but also to align with a target user's style, tone, and topical focus. Existing retrieval-augmented approaches such as LaMP and PGraphRAG enrich profiles with…

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…

The proliferation of textual data containing sensitive personal information across various domains requires robust anonymization techniques to protect privacy and comply with regulations, while preserving data usability for diverse and…

Language modeling is a keystone task in natural language processing. When training a language model on sensitive information, differential privacy (DP) allows us to quantify the degree to which our private data is protected. However,…

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 "Writer's Integrity" framework introduces a paradigm shift in maintaining the sanctity of human-generated text in the realms of academia, research, and publishing. This innovative system circumvents the shortcomings of current AI…

As large language models (LLMs) rapidly advance and integrate into daily life, the privacy risks they pose are attracting increasing attention. We focus on a specific privacy risk where LLMs may help identify the authorship of anonymous…

Preference-based fine-tuning has become an important component in training large language models, and the data used at this stage may contain sensitive user information. A central question is how to design a differentially private pipeline…

On-device training is currently the most common approach for training machine learning (ML) models on private, distributed user data. Despite this, on-device training has several drawbacks: (1) most user devices are too small to train large…

Privacy-preserving releasing of complex data (e.g., image, text, audio) represents a long-standing challenge for the data mining research community. Due to rich semantics of the data and lack of a priori knowledge about the analysis task,…

Retrieval-Augmented Generation (RAG) has emerged as the dominant technique to provide \emph{Large Language Models} (LLM) with fresh and relevant context, mitigating the risk of hallucinations and improving the overall quality of responses…

Privacy is important considering the financial Domain as such data is highly confidential and sensitive. Natural Language Processing (NLP) techniques can be applied for text classification and entity detection purposes in financial domains…

Privacy-preserving machine learning algorithms are crucial for the increasingly common setting in which personal data, such as medical or financial records, are analyzed. We provide general techniques to produce privacy-preserving…

In this paper, we introduce a novel concept of user-entity differential privacy (UeDP) to provide formal privacy protection simultaneously to both sensitive entities in textual data and data owners in learning natural language models…

Text-based analysis methods allow to reveal privacy relevant author attributes such as gender, age and identify of the text's author. Such methods can compromise the privacy of an anonymous author even when the author tries to remove…

In this paper we propose use of a k-anonymity-like approach for evaluating the privacy of redacted text. Given a piece of redacted text we use a state of the art transformer-based deep learning network to reconstruct the original text. This…

We address the challenge of ensuring differential privacy (DP) guarantees in training deep retrieval systems. Training these systems often involves the use of contrastive-style losses, which are typically non-per-example decomposable,…

For sensitive text data to be shared among NLP researchers and practitioners, shared documents need to comply with data protection and privacy laws. There is hence a growing interest in automated approaches for text anonymization. However,…

As LLMs rapidly advance and enter real-world use, their privacy implications are increasingly important. We study an authorship de-anonymization threat: using LLMs to link anonymous documents to their authors, potentially compromising…

Differentially private text sanitization refers to the process of privatizing texts under the framework of Differential Privacy (DP), providing provable privacy guarantees while also empirically defending against adversaries seeking to harm…