English
Related papers

Related papers: Characterizing Stereotypical Bias from Privacy-pre…

200 papers

The task of $\textit{Differentially Private Text Rewriting}$ is a class of text privatization techniques in which (sensitive) input textual documents are $\textit{rewritten}$ under Differential Privacy (DP) guarantees. The motivation behind…

Cryptography and Security · Computer Science 2025-03-31 Stephen Meisenbacher , Chaeeun Joy Lee , Florian Matthes

Natural Language Processing (NLP) techniques can be applied to help with the diagnosis of medical conditions such as depression, using a collection of a person's utterances. Depression is a serious medical illness that can have adverse…

Computation and Language · Computer Science 2022-06-17 Priyam Basu , Tiasa Singha Roy , Rakshit Naidu , Zumrut Muftuoglu , Sahib Singh , Fatemehsadat Mireshghallah

Natural language reflects our private lives and identities, making its privacy concerns as broad as those of real life. Language models lack the ability to understand the context and sensitivity of text, and tend to memorize phrases present…

Machine Learning · Statistics 2022-02-15 Hannah Brown , Katherine Lee , Fatemehsadat Mireshghallah , Reza Shokri , Florian Tramèr

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

Large scale adoption of large language models has introduced a new era of convenient knowledge transfer for a slew of natural language processing tasks. However, these models also run the risk of undermining user trust by exposing unwanted…

Computation and Language · Computer Science 2022-04-21 Richard Plant , Valerio Giuffrida , Dimitra Gkatzia

Many works at the intersection of Differential Privacy (DP) in Natural Language Processing aim to protect privacy by transforming texts under DP guarantees. This can be performed in a variety of ways, from word perturbations to full…

Computation and Language · Computer Science 2025-08-29 Stephen Meisenbacher , Maulik Chevli , Florian Matthes

Fine-tuning large language models (LLMs) has become an essential strategy for adapting them to specialized tasks; however, this process introduces significant privacy challenges, as sensitive training data may be inadvertently memorized and…

Cryptography and Security · Computer Science 2025-05-02 Hao Du , Shang Liu , Yang Cao

Neural language models are known to have a high capacity for memorization of training samples. This may have serious privacy implications when training models on user content such as email correspondence. Differential privacy (DP), a…

Rapid advances in Natural Language Processing (NLP) have revolutionized many fields, including healthcare. However, these advances raise significant privacy concerns, especially when pre-trained models fine-tuned and specialized on…

Computation and Language · Computer Science 2026-05-21 Antoine Boutet , Lucas Magnana , Juliette Sénéchal

The study of Differential Privacy (DP) in Natural Language Processing often views the task of text privatization as a $\textit{rewriting}$ task, in which sensitive input texts are rewritten to hide explicit or implicit private information.…

Computation and Language · Computer Science 2024-06-03 Stephen Meisenbacher , Florian Matthes

Differential Privacy (DP) is an important privacy-enhancing technology for private machine learning systems. It allows to measure and bound the risk associated with an individual participation in a computation. However, it was recently…

Machine Learning · Computer Science 2022-09-09 Cuong Tran , My H. Dinh , Ferdinando Fioretto

One of the big challenges in machine learning applications is that training data can be different from the real-world data faced by the algorithm. In language modeling, users' language (e.g. in private messaging) could change in a year and…

Computation and Language · Computer Science 2018-03-07 Vadim Popov , Mikhail Kudinov , Irina Piontkovskaya , Petr Vytovtov , Alex Nevidomsky

As the issues of privacy and trust are receiving increasing attention within the research community, various attempts have been made to anonymize textual data. A significant subset of these approaches incorporate differentially private…

Cryptography and Security · Computer Science 2022-05-05 Justus Mattern , Benjamin Weggenmann , Florian Kerschbaum

We address the problem of how to "obfuscate" texts by removing stylistic clues which can identify authorship, whilst preserving (as much as possible) the content of the text. In this paper we combine ideas from "generalised differential…

Cryptography and Security · Computer Science 2019-02-06 Natasha Fernandes , Mark Dras , Annabelle McIver

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…

Computation and Language · Computer Science 2021-10-06 Priyam Basu , Tiasa Singha Roy , Rakshit Naidu , Zumrut Muftuoglu

Fine-tuning large language models (LLMs) for specific tasks introduces privacy risks, as models may inadvertently memorise and leak sensitive training data. While Differential Privacy (DP) offers a solution to mitigate these risks, it…

Machine Learning · Computer Science 2024-11-26 Olivia Ma , Jonathan Passerat-Palmbach , Dmitrii Usynin

Differential privacy (DP) is a popular mechanism for training machine learning models with bounded leakage about the presence of specific points in the training data. The cost of differential privacy is a reduction in the model's accuracy.…

Machine Learning · Computer Science 2019-10-29 Eugene Bagdasaryan , Vitaly Shmatikov

To protect the privacy of individuals whose data is being shared, it is of high importance to develop methods allowing researchers and companies to release textual data while providing formal privacy guarantees to its originators. In the…

Machine Learning · Computer Science 2022-10-27 Justus Mattern , Zhijing Jin , Benjamin Weggenmann , Bernhard Schoelkopf , Mrinmaya Sachan

The article introduces a method for extracting words of different degrees of importance based on the BERT pre-training model and proves the effectiveness of this method. The article also discusses the impact of maintaining the same…

Computation and Language · Computer Science 2024-09-06 Qingwen Fu

Recent research shows that large language models are susceptible to privacy attacks that infer aspects of the training data. However, it is unclear if simpler generative models, like topic models, share similar vulnerabilities. In this…

Cryptography and Security · Computer Science 2024-09-24 Nico Manzonelli , Wanrong Zhang , Salil Vadhan