Privacy Preserving In-Context-Learning Framework for Large Language Models
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866914163929907200 |
|---|---|
| author | Bhusal, Bishnu Acharya, Manoj Kaur, Ramneet Samplawski, Colin Roy, Anirban Cobb, Adam D. Chadha, Rohit Jha, Susmit |
| author_facet | Bhusal, Bishnu Acharya, Manoj Kaur, Ramneet Samplawski, Colin Roy, Anirban Cobb, Adam D. Chadha, Rohit Jha, Susmit |
| contents | 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 leakage, where adversaries can extract sensitive information embedded in the prompts. In this work, we introduce a novel private prediction framework for generating high-quality synthetic text with strong privacy guarantees. Our approach leverages the Differential Privacy (DP) framework to ensure worst-case theoretical bounds on information leakage without requiring any fine-tuning of the underlying models. The proposed method performs inference on private records and aggregates the resulting per-token output distributions. This enables the generation of longer and coherent synthetic text while maintaining privacy guarantees. Additionally, we propose a simple blending operation that combines private and public inference to further enhance utility. Empirical evaluations demonstrate that our approach outperforms previous state-of-the-art methods on in-context-learning (ICL) tasks, making it a promising direction for privacy-preserving text generation while maintaining high utility. Our code is available at https://github.com/bhusalb/privacy-preserving-icl. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2509_13625 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Privacy Preserving In-Context-Learning Framework for Large Language Models Bhusal, Bishnu Acharya, Manoj Kaur, Ramneet Samplawski, Colin Roy, Anirban Cobb, Adam D. Chadha, Rohit Jha, Susmit Machine Learning Computation and Language Cryptography and Security 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 leakage, where adversaries can extract sensitive information embedded in the prompts. In this work, we introduce a novel private prediction framework for generating high-quality synthetic text with strong privacy guarantees. Our approach leverages the Differential Privacy (DP) framework to ensure worst-case theoretical bounds on information leakage without requiring any fine-tuning of the underlying models. The proposed method performs inference on private records and aggregates the resulting per-token output distributions. This enables the generation of longer and coherent synthetic text while maintaining privacy guarantees. Additionally, we propose a simple blending operation that combines private and public inference to further enhance utility. Empirical evaluations demonstrate that our approach outperforms previous state-of-the-art methods on in-context-learning (ICL) tasks, making it a promising direction for privacy-preserving text generation while maintaining high utility. Our code is available at https://github.com/bhusalb/privacy-preserving-icl. |
| title | Privacy Preserving In-Context-Learning Framework for Large Language Models |
| topic | Machine Learning Computation and Language Cryptography and Security |
| url | https://arxiv.org/abs/2509.13625 |