English
Related papers

Related papers: Truthful Text Sanitization Guided by Inference Att…

200 papers

Retrieval-augmented generation and tool-integrated LLM agents increasingly depend on external textual sources. This reliance broadens the available attack surface, allowing adversaries to insert malicious instructions that trigger…

Cryptography and Security · Computer Science 2026-05-05 Soumil Datta , Melissa Umble , Daniel S. Brown , Guanhong Tao

Unstructured text from legal, medical, and administrative sources offers a rich but underutilized resource for research in public health and the social sciences. However, large-scale analysis is hampered by two key challenges: the presence…

Computation and Language · Computer Science 2025-07-16 Anders Ledberg , Anna Thalén

Privacy has become a serious concern for modern Information Societies. The sensitive nature of much of the data that are daily exchanged or released to untrusted parties requires that responsible organizations undertake appropriate privacy…

Cryptography and Security · Computer Science 2017-01-03 David Sánchez , Montserrat Batet

The emerging success of large language models (LLMs) heavily relies on collecting abundant training data from external (untrusted) sources. Despite substantial efforts devoted to data cleaning and curation, well-constructed LLMs have been…

Computation and Language · Computer Science 2024-02-26 Tianlin Li , Qian Liu , Tianyu Pang , Chao Du , Qing Guo , Yang Liu , Min Lin

Large language models (LLMs) have significantly transformed natural language understanding and generation, but they raise privacy concerns due to potential exposure of sensitive information. Studies have highlighted the risk of information…

Machine Learning · Computer Science 2025-11-20 Bishnu Bhusal , Manoj Acharya , Ramneet Kaur , Colin Samplawski , Anirban Roy , Adam D. Cobb , Rohit Chadha , Susmit Jha

Web-based Large Language Model (LLM) services have been widely adopted and have become an integral part of our Internet experience. Third-party plugins enhance the functionalities of LLM by enabling access to real-world data and services.…

Cryptography and Security · Computer Science 2025-12-04 Chun Jie Chong , Chenxi Hou , Zhihao Yao , Seyed Mohammadjavad Seyed Talebi

Large language models (LLMs) are increasingly used in modern search and answer systems to synthesize multiple, sometimes conflicting, texts into a single response, yet current pipelines offer weak incentives for sources to be accurate and…

Computation and Language · Computer Science 2026-02-26 Yanchen Jiang , Zhe Feng , Aranyak Mehta

In the realm of data privacy, the ability to effectively anonymise text is paramount. With the proliferation of deep learning and, in particular, transformer architectures, there is a burgeoning interest in leveraging these advanced models…

Metric Differential Privacy is a generalization of differential privacy tailored to address the unique challenges of text-to-text privatization. By adding noise to the representation of words in the geometric space of embeddings, words are…

Computation and Language · Computer Science 2023-06-05 Stefan Arnold , Dilara Yesilbas , Sven Weinzierl

Adversarial purification is a successful defense mechanism against adversarial attacks without requiring knowledge of the form of the incoming attack. Generally, adversarial purification aims to remove the adversarial perturbations…

Computation and Language · Computer Science 2023-05-04 Linyang Li , Demin Song , Xipeng Qiu

The increasing use of Artificial Intelligence (AI) technologies, such as Large Language Models (LLMs) has led to nontrivial improvements in various tasks, including accurate authorship identification of documents. However, while LLMs…

Computation and Language · Computer Science 2025-03-26 Kenneth Alperin , Rohan Leekha , Adaku Uchendu , Trang Nguyen , Srilakshmi Medarametla , Carlos Levya Capote , Seth Aycock , Charlie Dagli

Text simplification (TS) refers to the process of reducing the complexity of a text while retaining its original meaning and key information. Existing work only shows that large language models (LLMs) have outperformed supervised…

Computation and Language · Computer Science 2025-02-13 Jipeng Qiang , Minjiang Huang , Yi Zhu , Yunhao Yuan , Chaowei Zhang , Kui Yu

This work introduces an anonymization scheme for a corpus of texts to safeguard metadata from disclosure. It specifically aims to prevent large language models from identifying metadata associated with texts, thereby avoiding their…

Applications · Statistics 2025-05-28 Jan Greve , Lukas Sablica

Machine Learning approaches to Natural Language Processing tasks benefit from a comprehensive collection of real-life user data. At the same time, there is a clear need for protecting the privacy of the users whose data is collected and…

Computation and Language · Computer Science 2022-11-16 David Ifeoluwa Adelani , Ali Davody , Thomas Kleinbauer , Dietrich Klakow

This work investigates the effectiveness of different pseudonymization techniques, ranging from rule-based substitutions to using pre-trained Large Language Models (LLMs), on a variety of datasets and models used for two widely used NLP…

Computation and Language · Computer Science 2023-06-12 Oleksandr Yermilov , Vipul Raheja , Artem Chernodub

Data sanitization in the context of language modeling involves identifying sensitive content, such as personally identifiable information (PII), and redacting them from a dataset corpus. It is a common practice used in natural language…

Computation and Language · Computer Science 2024-11-12 Anwesan Pal , Radhika Bhargava , Kyle Hinsz , Jacques Esterhuizen , Sudipta Bhattacharya

We present a novel benchmark and associated evaluation metrics for assessing the performance of text anonymization methods. Text anonymization, defined as the task of editing a text document to prevent the disclosure of personal…

Computation and Language · Computer Science 2022-07-04 Ildikó Pilán , Pierre Lison , Lilja Øvrelid , Anthi Papadopoulou , David Sánchez , Montserrat Batet

This paper focuses on text detoxification, i.e., automatically converting toxic text into non-toxic text. This task contributes to safer and more respectful online communication and can be considered a Text Style Transfer (TST) task, where…

Computation and Language · Computer Science 2024-06-11 Sourabrata Mukherjee , Akanksha Bansal , Atul Kr. Ojha , John P. McCrae , Ondřej Dušek

Differential privacy (DP) is the de facto privacy standard against privacy leakage attacks, including many recently discovered ones against large language models (LLMs). However, we discovered that LLMs could reconstruct the altered/removed…

Cryptography and Security · Computer Science 2025-09-19 Shuchao Pang , Zhigang Lu , Haichen Wang , Peng Fu , Yongbin Zhou , Minhui Xue

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…

Cryptography and Security · Computer Science 2026-04-17 Lirui Zhang , Huishuai Zhang