paper-with-me

Papers

Token-Level Privacy in Large Language Models

2025-03-05 · Re'em Harel, Niv Gilboa, Yuval Pinter

The use of language models as remote services requires transmitting private information to external providers, raising significant privacy concerns. This process not only risks exposing sensitive data to untrusted service providers but also leaves it vulnerable to interception by eavesdroppers. Existing privacy-preserving methods for natural language processing (NLP) interactions primarily rely on semantic similarity, overlooking the role of contextual information. In this work, we introduce dchi-stencil, a novel token-level privacy-preserving mechanism that integrates contextual and semantic information while ensuring strong privacy guarantees under the dchi differential privacy framework, achieving 2epsilon-dchi-privacy. By incorporating both semantic and contextual nuances, dchi-stencil achieves a robust balance between privacy and utility. We evaluate dchi-stencil using state-of-the-art language models and diverse datasets, achieving comparable and even better trade-off between utility and privacy compared to existing methods. This work highlights the potential of dchi-stencil to set a new standard for privacy-preserving NLP in modern, high-risk applications.

📄 PDF Abstract BibTeX arXiv:2503.03652

Code (0)

등록된 구현이 없습니다.

Tasks

Privacy PreservingSemantic SimilaritySemantic Textual Similarity

Methods 이 논문이 사용한 방법론

Golden Queue Managers 설명 없음
SET Dynamic Sparse Training method where weight mask is updated randomly periodically

Similar Papers 제목 키워드 기반

Tokens for Learning, Tokens for Unlearning: Mitigating Membership Inference Attacks in Large Language Models via Dual-Purpose Training

2025-02-27 · Toan Tran, Ruixuan Liu, Li Xiong

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…

Language ModelingLanguage Modelling

DP-Fusion: Token-Level Differentially Private Inference for Large Language Models

2025-07-06 · Rushil Thareja, Preslav Nakov, Praneeth Vepakomma, Nils Lukas arxiv

Large language models (LLMs) do not preserve privacy at inference-time. The LLM's outputs can inadvertently reveal information about the model's context, which presents a privacy challenge when the LLM is augmented via t…

(Token-Level) InfoRMIA: Stronger Membership Inference and Memorization Assessment for LLMs

2025-10-07 · Jiashu Tao, Reza Shokri arxiv

Machine learning models are known to leak sensitive information, as they inevitably memorize (parts of) their training data. More alarmingly, large language models (LLMs) are now trained on nearly all available data, whi…

Computational Efficiency

Differential Privacy in Generative AI Agents: Analysis and Optimal Tradeoffs

2026-03-18 · Ya-Ting Yang, Quanyan Zhu arxiv

Large language models (LLMs) and AI agents are increasingly integrated into enterprise systems to access internal databases and generate context-aware responses. While such integration improves productivity and decision …

Response Generation

Data-Free Privacy-Preserving for LLMs via Model Inversion and Selective Unlearning

2026-01-22 · Xinjie Zhou, Zhihui Yang, Lechao Cheng, Sai Wu 외 arxiv

Large language models (LLMs) exhibit powerful capabilities but risk memorizing sensitive personally identifiable information (PII) from their training data, posing significant privacy concerns. While machine unlearning t…