Public Data Assisted Differentially Private In-Context Learning

• URL: http://arxiv.org/abs/2509.10932v1
• Date: Sat, 13 Sep 2025 18:11:51 GMT
• Title: Public Data Assisted Differentially Private In-Context Learning
• Authors: Seongho Joo, Hyukhun Koh, Kyomin Jung,
• Abstract summary: In-context learning (ICL) in Large Language Models (LLMs) has shown remarkable performance across various tasks without requiring fine-tuning.<n>Recent studies have highlighted the risk of private data leakage through the prompt in ICL.<n>We propose a private in-context learning algorithm that effectively balances privacy protection and model utility.
• Score: 19.92751862281067
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: 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 ICL, especially when LLMs are exposed to malicious attacks. While differential privacy (DP) provides strong privacy guarantees, it often significantly reduces the utility of in-context learning (ICL). To address this challenge, we incorporate task-related public data into the ICL framework while maintaining the DP guarantee. Based on this approach, we propose a private in-context learning algorithm that effectively balances privacy protection and model utility. Through experiments, we demonstrate that our approach significantly improves the utility of private ICL with the assistance of public data. Additionally, we show that our method is robust against membership inference attacks, demonstrating empirical privacy protection.

Related papers

• Contextualized Privacy Defense for LLM Agents [84.30907378390512]
  LLM agents increasingly act on users' personal information, yet existing privacy defenses remain limited in both design and adaptability.<n>We propose Contextualized Defense Instructing (CDI), a new privacy defense paradigm.<n>We show that our CDI consistently achieves a better balance between privacy preservation (94.2%) and helpfulness (80.6%) than baselines.
  arXiv  Detail & Related papers  (2026-03-03T13:35:33Z)
• Private PoEtry: Private In-Context Learning via Product of Experts [58.496468062236225]
  In-context learning (ICL) enables Large Language Models to adapt to new tasks with only a small set of examples at inference time.<n>Existing differential privacy approaches to ICL are either computationally expensive or rely on oversampling, synthetic data generation, or unnecessary thresholding.<n>We reformulate private ICL through the lens of a Product-of-Experts model. This gives a theoretically grounded framework, and the algorithm can be trivially parallelized.<n>We find that our method improves accuracy by more than 30 percentage points on average compared to prior DP-ICL methods, while maintaining strong privacy guarantees.
  arXiv  Detail & Related papers  (2026-02-04T19:56:24Z)
• PBa-LLM: Privacy- and Bias-aware NLP using Named-Entity Recognition (NER) [45.870212237420226]
  This work explores the use of Named- Entity Recognition (NER) to facilitate the privacy-preserving training of Large Language Models (LLMs)<n>We propose a framework that uses NER technologies to anonymize sensitive information in text data, such as personal identities or geographic locations.<n>The study involved two language models (BERT and RoBERTa) and six anonymization algorithms (based on Presidio, FLAIR, BERT, and different versions of GPT) applied to a database of 24,000 candidate profiles.
  arXiv  Detail & Related papers  (2025-06-30T14:42:49Z)
• Urania: Differentially Private Insights into AI Use [104.7449031243196]
  $Urania$ provides end-to-end privacy protection by leveraging DP tools such as clustering, partition selection, and histogram-based summarization.<n>Results show the framework's ability to extract meaningful conversational insights while maintaining stringent user privacy.
  arXiv  Detail & Related papers  (2025-06-05T07:00:31Z)
• Privacy in Fine-tuning Large Language Models: Attacks, Defenses, and Future Directions [11.338466798715906]
  Fine-tuning Large Language Models (LLMs) can achieve state-of-the-art performance across various domains.<n>This paper provides a comprehensive survey of privacy challenges associated with fine-tuning LLMs.<n>We highlight vulnerabilities to various privacy attacks, including membership inference, data extraction, and backdoor attacks.
  arXiv  Detail & Related papers  (2024-12-21T06:41:29Z)
• Differentially Private Deep Model-Based Reinforcement Learning [47.651861502104715]
  We introduce PriMORL, a model-based RL algorithm with formal differential privacy guarantees. PriMORL learns an ensemble of trajectory-level DP models of the environment from offline data.
  arXiv  Detail & Related papers  (2024-02-08T10:05:11Z)
• Privacy Preserving Large Language Models: ChatGPT Case Study Based Vision and Framework [6.828884629694705]
  This article proposes the conceptual model called PrivChatGPT, a privacy-generative model for LLMs. PrivChatGPT consists of two main components i.e., preserving user privacy during the data curation/pre-processing together with preserving private context and the private training process for large-scale data.
  arXiv  Detail & Related papers  (2023-10-19T06:55:13Z)
• PrivacyMind: Large Language Models Can Be Contextual Privacy Protection Learners [81.571305826793]
  We introduce Contextual Privacy Protection Language Models (PrivacyMind) Our work offers a theoretical analysis for model design and benchmarks various techniques. In particular, instruction tuning with both positive and negative examples stands out as a promising method.
  arXiv  Detail & Related papers  (2023-10-03T22:37:01Z)
• Privacy-Preserving In-Context Learning with Differentially Private Few-Shot Generation [37.55812121348268]
  In-context learning (ICL) with large language models (LLMs) on private datasets poses privacy risks. We propose a novel algorithm that generates synthetic few-shot demonstrations from the private dataset with formal differential privacy guarantees.
  arXiv  Detail & Related papers  (2023-09-21T03:59:00Z)
• Privacy-Preserving In-Context Learning for Large Language Models [36.13851291571231]
  In-context learning (ICL) is an important capability of Large Language Models (LLMs) LLMs's responses may leak the sensitive private information contained in in-context exemplars. We propose Differentially Private In-context Learning (DP-ICL), a general paradigm for privatizing ICL tasks.
  arXiv  Detail & Related papers  (2023-05-02T17:52:58Z)
• Offline Reinforcement Learning with Differential Privacy [16.871660060209674]
  offline reinforcement learning problem is often motivated by the need to learn data-driven decision policies in financial, legal and healthcare applications. We design offline RL algorithms with differential privacy guarantees which provably prevent such risks.
  arXiv  Detail & Related papers  (2022-06-02T00:45:04Z)
• Distributed Machine Learning and the Semblance of Trust [66.1227776348216]
  Federated Learning (FL) allows the data owner to maintain data governance and perform model training locally without having to share their data. FL and related techniques are often described as privacy-preserving. We explain why this term is not appropriate and outline the risks associated with over-reliance on protocols that were not designed with formal definitions of privacy in mind.
  arXiv  Detail & Related papers  (2021-12-21T08:44:05Z)
• Private Reinforcement Learning with PAC and Regret Guarantees [69.4202374491817]
  We design privacy preserving exploration policies for episodic reinforcement learning (RL) We first provide a meaningful privacy formulation using the notion of joint differential privacy (JDP) We then develop a private optimism-based learning algorithm that simultaneously achieves strong PAC and regret bounds, and enjoys a JDP guarantee.
  arXiv  Detail & Related papers  (2020-09-18T20:18:35Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.