English
Related papers

Related papers: Protecting User Prompts Via Character-Level Differ…

200 papers

Accurate privacy evaluation of textual data remains a critical challenge in privacy-preserving natural language processing. Recent work has shown that large language models (LLMs) can serve as reliable privacy evaluators, achieving strong…

Computation and Language · Computer Science 2026-04-01 Gabriel Loiseau , Damien Sileo , Damien Riquet , Maxime Meyer , Marc Tommasi

Large Language Models (LLMs) are highly vulnerable to input perturbations, as even a small prompt change may result in a substantially different output. Existing methods to enhance LLM robustness are primarily focused on perturbed data…

Computation and Language · Computer Science 2025-04-04 Aryan Agrawal , Lisa Alazraki , Shahin Honarvar , Marek Rei

The widespread adoption of Large Language Models (LLMs) has raised significant privacy concerns regarding the exposure of personally identifiable information (PII) in user prompts. To address this challenge, we propose a query-unrelated PII…

Cryptography and Security · Computer Science 2026-02-18 Hao Shen , Zhouhong Gu , Haokai Hong , Weili Han

As sufficient data are not always publically accessible for model training, researchers exploit limited data with advanced learning algorithms or expand the dataset via data augmentation (DA). Conducting DA in private domain requires…

Computation and Language · Computer Science 2024-02-27 Yiping Song , Juhua Zhang , Zhiliang Tian , Yuxin Yang , Minlie Huang , Dongsheng Li

Large language models (LLMs) exhibit robust capabilities in text generation and comprehension, mimicking human behavior and exhibiting synthetic personalities. However, some LLMs have displayed offensive personality, propagating toxic…

Computation and Language · Computer Science 2024-06-10 Yanquan Chen , Zhen Wu , Junjie Guo , Shujian Huang , Xinyu Dai

In-context learning (ICL) in Large Language Models (LLMs) has shown remarkable performance across various tasks without requiring fine-tuning. However, recent studies have highlighted the risk of private data leakage through the prompt in…

Artificial Intelligence · Computer Science 2025-09-16 Seongho Joo , Hyukhun Koh , Kyomin Jung

Large language models (LLMs), like ChatGPT, have greatly simplified text generation tasks. However, they have also raised concerns about privacy risks such as data leakage and unauthorized data collection. Existing solutions for…

Cryptography and Security · Computer Science 2026-03-19 Meng Tong , Kejiang Chen , Jie Zhang , Yuang Qi , Weiming Zhang , Nenghai Yu , Tianwei Zhang , Zhikun Zhang

While communication strategies of Large Language Models (LLMs) are crucial for human-LLM interactions, they can also be weaponized to elicit private information, yet such stealthy attacks remain under-explored. This paper introduces the…

Human-Computer Interaction · Computer Science 2025-11-18 Shuning Zhang , Jiaqi Bai , Linzhi Wang , Shixuan Li , Xin Yi , Hewu Li

In-context learning (ICL) is an important capability of Large Language Models (LLMs), enabling these models to dynamically adapt based on specific, in-context exemplars, thereby improving accuracy and relevance. However, LLM's responses may…

Machine Learning · Computer Science 2023-10-03 Tong Wu , Ashwinee Panda , Jiachen T. Wang , Prateek Mittal

With the widespread application of large language models (LLMs), user privacy protection has become a significant research topic. Existing privacy preference modeling methods often rely on large-scale user data, making effective privacy…

Cryptography and Security · Computer Science 2025-05-13 Haowei Yang , Qingyi Lu , Yang Wang , Sibei Liu , Jiayun Zheng , Ao Xiang

Large Language Models (LLMs) have a privacy concern because they memorize training data (including personally identifiable information (PII) like emails and phone numbers) and leak it during inference. A company can train an LLM on its…

Cryptography and Security · Computer Science 2023-07-21 Jaydeep Borkar

Large language models (LLMs) are primarily accessed via commercial APIs, but this often requires users to expose their data to service providers. In this paper, we explore how users can stay in control of their data by using privacy…

Computation and Language · Computer Science 2025-10-21 Guillem Ramírez , Alexandra Birch , Ivan Titov

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…

Computation and Language · Computer Science 2024-07-10 Jiajia Li , Lu Yang , Letian Peng , Shitou Zhang , Ping Wang , Zuchao Li , Hai Zhao

Large language models (LLMs) are designed to align with human values in their responses. This study exploits LLMs with an iterative prompting technique where each prompt is systematically modified and refined across multiple iterations to…

Computation and Language · Computer Science 2025-03-27 Shih-Wen Ke , Guan-Yu Lai , Guo-Lin Fang , Hsi-Yuan Kao

Due to the sensitive nature of personally identifiable information (PII), its owners may have the authority to control its inclusion or request its removal from large-language model (LLM) training. Beyond this, PII may be added or removed…

Computation and Language · Computer Science 2025-06-27 Jaydeep Borkar , Matthew Jagielski , Katherine Lee , Niloofar Mireshghallah , David A. Smith , Christopher A. Choquette-Choo

Language models (LMs) may memorize personally identifiable information (PII) from training data, enabling adversaries to extract it during inference. Existing defense mechanisms such as differential privacy (DP) reduce this leakage, but…

Cryptography and Security · Computer Science 2026-02-27 Anthony Hughes , Vasisht Duddu , N. Asokan , Nikolaos Aletras , Ning Ma

Large Language Models (LLMs) can generate human-like disinformation, yet their ability to personalise such content across languages and demographics remains underexplored. This study presents the first large-scale, multilingual analysis of…

Computation and Language · Computer Science 2025-10-30 João A. Leite , Arnav Arora , Silvia Gargova , João Luz , Gustavo Sampaio , Ian Roberts , Carolina Scarton , Kalina Bontcheva

We surface a new threat to closed-weight Large Language Models (LLMs) that enables an attacker to compute optimization-based prompt injections. Specifically, we characterize how an attacker can leverage the loss-like information returned…

Cryptography and Security · Computer Science 2025-05-13 Andrey Labunets , Nishit V. Pandya , Ashish Hooda , Xiaohan Fu , Earlence Fernandes

This paper introduces a vision of confidential prompting: securing user prompts from an untrusted, cloud-hosted large language model (LLM) while preserving model confidentiality, output invariance, and compute efficiency. As a first step…

Cryptography and Security · Computer Science 2025-11-20 Caihua Li , In Gim , Lin Zhong

Differentially-private mechanisms for text generation typically add carefully calibrated noise to input words and use the nearest neighbor to the noised input as the output word. When the noise is small in magnitude, these mechanisms are…

Computation and Language · Computer Science 2021-04-27 Zekun Xu , Abhinav Aggarwal , Oluwaseyi Feyisetan , Nathanael Teissier