Private Text Generation by Seeding Large Language Model Prompts

• URL: http://arxiv.org/abs/2502.13193v1
• Date: Tue, 18 Feb 2025 16:50:38 GMT
• Title: Private Text Generation by Seeding Large Language Model Prompts
• Authors: Supriya Nagesh, Justin Y. Chen, Nina Mishra, Tal Wagner,
• Abstract summary: We propose Differentially Private Keyphrase Prompt Seeding (DP-KPS), a method that generates a private synthetic text corpus from a sensitive input corpus. We evaluate DP-KPS on downstream ML text classification tasks, and show that the corpora it generates preserve much of the predictive power of the original ones.
• Score: 13.407214545457778
• License:
• Abstract: We explore how private synthetic text can be generated by suitably prompting a large language model (LLM). This addresses a challenge for organizations like hospitals, which hold sensitive text data like patient medical records, and wish to share it in order to train machine learning models for medical tasks, while preserving patient privacy. Methods that rely on training or finetuning a model may be out of reach, either due to API limits of third-party LLMs, or due to ethical and legal prohibitions on sharing the private data with the LLM itself. We propose Differentially Private Keyphrase Prompt Seeding (DP-KPS), a method that generates a private synthetic text corpus from a sensitive input corpus, by accessing an LLM only through privatized prompts. It is based on seeding the prompts with private samples from a distribution over phrase embeddings, thus capturing the input corpus while achieving requisite output diversity and maintaining differential privacy. We evaluate DP-KPS on downstream ML text classification tasks, and show that the corpora it generates preserve much of the predictive power of the original ones. Our findings offer hope that institutions can reap ML insights by privately sharing data with simple prompts and little compute.

Related papers

• Idiosyncrasies in Large Language Models [54.26923012617675]
  We unveil and study idiosyncrasies in Large Language Models (LLMs) We find that fine-tuning existing text embedding models on LLM-generated texts yields excellent classification accuracy. We leverage LLM as judges to generate detailed, open-ended descriptions of each model's idiosyncrasies.
  arXiv  Detail & Related papers  (2025-02-17T18:59:02Z)
• Differentially Private Steering for Large Language Model Alignment [55.30573701583768]
  We present the first study of aligning Large Language Models with private datasets. Our work proposes the textitunderlinePrivate underlineSteering for LLM underlineAment (PSA) algorithm. Our results show that PSA achieves DP guarantees for LLM alignment with minimal loss in performance.
  arXiv  Detail & Related papers  (2025-01-30T17:58:36Z)
• Private prediction for large-scale synthetic text generation [28.488459921169905]
  We present an approach for generating differentially private synthetic text using large language models (LLMs) In the private prediction framework, we only require the output synthetic data to satisfy differential privacy guarantees.
  arXiv  Detail & Related papers  (2024-07-16T18:28:40Z)
• On Protecting the Data Privacy of Large Language Models (LLMs): A Survey [35.48984524483533]
  Large language models (LLMs) are complex artificial intelligence systems capable of understanding, generating and translating human language. LLMs process and generate large amounts of data, which may threaten data privacy.
  arXiv  Detail & Related papers  (2024-03-08T08:47:48Z)
• Differentially Private Synthetic Data via Foundation Model APIs 2: Text [56.13240830670327]
  A lot of high-quality text data generated in the real world is private and cannot be shared or used freely due to privacy concerns. We propose an augmented PE algorithm, named Aug-PE, that applies to the complex setting of text. Our results demonstrate that Aug-PE produces DP synthetic text that yields competitive utility with the SOTA DP finetuning baselines.
  arXiv  Detail & Related papers  (2024-03-04T05:57:50Z)
• DP-OPT: Make Large Language Model Your Privacy-Preserving Prompt Engineer [57.04801796205638]
  Large Language Models (LLMs) have emerged as dominant tools for various tasks. However, concerns surrounding data privacy present obstacles due to the tuned prompts' dependency on sensitive private information. We present Differentially-Private Offsite Prompt Tuning (DP-OPT) to address this challenge.
  arXiv  Detail & Related papers  (2023-11-27T02:01:10Z)
• Can LLMs Keep a Secret? Testing Privacy Implications of Language Models via Contextual Integrity Theory [82.7042006247124]
  We show that even the most capable AI models reveal private information in contexts that humans would not, 39% and 57% of the time, respectively. Our work underscores the immediate need to explore novel inference-time privacy-preserving approaches, based on reasoning and theory of mind.
  arXiv  Detail & Related papers  (2023-10-27T04:15:30Z)
• 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)
• Are Chatbots Ready for Privacy-Sensitive Applications? An Investigation into Input Regurgitation and Prompt-Induced Sanitization [4.01610127647615]
  ChatGPT would retain personally identifiable information (PII) verbatim in 57.4% of cases. We probe ChatGPT's perception of privacy-related policies and mechanisms by directly instructing it to provide compliant outputs.
  arXiv  Detail & Related papers  (2023-05-24T10:48:05Z)
• CAPE: Context-Aware Private Embeddings for Private Language Learning [0.5156484100374058]
  Context-Aware Private Embeddings (CAPE) is a novel approach which preserves privacy during training of embeddings. CAPE applies calibrated noise through differential privacy, preserving the encoded semantic links while obscuring sensitive information. Experimental results demonstrate that the proposed approach reduces private information leakage better than either single intervention.
  arXiv  Detail & Related papers  (2021-08-27T14:50:12Z)

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.