PAPILLON: PrivAcy Preservation from Internet-based and Local Language MOdel ENsembles

• URL: http://arxiv.org/abs/2410.17127v1
• Date: Tue, 22 Oct 2024 16:00:26 GMT
• Title: PAPILLON: PrivAcy Preservation from Internet-based and Local Language MOdel ENsembles
• Authors: Li Siyan, Vethavikashini Chithrra Raghuram, Omar Khattab, Julia Hirschberg, Zhou Yu,
• Abstract summary: We propose Privacy-Conscious Delegation, a novel task for chaining API-based and local models. We utilize recent public collections of user-LLM interactions to construct a natural benchmark called PUPA. Our best pipeline maintains high response quality for 85.5% of user queries while restricting privacy leakage to only 7.5%.
• Score: 21.340456482528136
• License:
• Abstract: Users can divulge sensitive information to proprietary LLM providers, raising significant privacy concerns. While open-source models, hosted locally on the user's machine, alleviate some concerns, models that users can host locally are often less capable than proprietary frontier models. Toward preserving user privacy while retaining the best quality, we propose Privacy-Conscious Delegation, a novel task for chaining API-based and local models. We utilize recent public collections of user-LLM interactions to construct a natural benchmark called PUPA, which contains personally identifiable information (PII). To study potential approaches, we devise PAPILLON, a multi-stage LLM pipeline that uses prompt optimization to address a simpler version of our task. Our best pipeline maintains high response quality for 85.5% of user queries while restricting privacy leakage to only 7.5%. We still leave a large margin to the generation quality of proprietary LLMs for future work. Our data and code will be available at https://github.com/siyan-sylvia-li/PAPILLON.

Related papers

• KnowledgeSG: Privacy-Preserving Synthetic Text Generation with Knowledge Distillation from Server [48.04903443425111]
  Large language models (LLMs) facilitate many parties to fine-tune LLMs on their own private data. Existing solutions, such as utilizing synthetic data for substitution, struggle to simultaneously improve performance and preserve privacy. We propose KnowledgeSG, a novel client-server framework which enhances synthetic data quality and improves model performance while ensuring privacy.
  arXiv  Detail & Related papers  (2024-10-08T06:42:28Z)
• PrivacyLens: Evaluating Privacy Norm Awareness of Language Models in Action [54.11479432110771]
  PrivacyLens is a novel framework designed to extend privacy-sensitive seeds into expressive vignettes and further into agent trajectories. We instantiate PrivacyLens with a collection of privacy norms grounded in privacy literature and crowdsourced seeds. State-of-the-art LMs, like GPT-4 and Llama-3-70B, leak sensitive information in 25.68% and 38.69% of cases, even when prompted with privacy-enhancing instructions.
  arXiv  Detail & Related papers  (2024-08-29T17:58:38Z)
• Are LLM-based methods good enough for detecting unfair terms of service? [67.49487557224415]
  Large language models (LLMs) are good at parsing long text-based documents. We build a dataset consisting of 12 questions applied individually to a set of privacy policies. Some open-source models are able to provide a higher accuracy compared to some commercial models.
  arXiv  Detail & Related papers  (2024-08-24T09:26:59Z)
• Mind the Privacy Unit! User-Level Differential Privacy for Language Model Fine-Tuning [62.224804688233]
  differential privacy (DP) offers a promising solution by ensuring models are 'almost indistinguishable' with or without any particular privacy unit. We study user-level DP motivated by applications where it necessary to ensure uniform privacy protection across users.
  arXiv  Detail & Related papers  (2024-06-20T13:54:32Z)
• PFID: Privacy First Inference Delegation Framework for LLMs [34.59282305562392]
  This paper introduces a novel privacy-preservation framework named PFID for LLMs. It addresses critical privacy concerns by localizing user data through model sharding and singular value decomposition.
  arXiv  Detail & Related papers  (2024-06-18T03:27:09Z)
• ConfusionPrompt: Practical Private Inference for Online Large Language Models [3.8134804426693094]
  State-of-the-art large language models (LLMs) are typically deployed as online services, requiring users to transmit detailed prompts to cloud servers. We introduce ConfusionPrompt, a novel framework for private LLM inference that protects user privacy by decomposing the original prompt into smaller sub-prompts. We show that ConfusionPrompt achieves significantly higher utility than local inference methods using open-source models and perturbation-based techniques.
  arXiv  Detail & Related papers  (2023-12-30T01:26:42Z)
• 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)
• PrivLM-Bench: A Multi-level Privacy Evaluation Benchmark for Language Models [42.20437015301152]
  We present PrivLM-Bench, a benchmark for evaluating the privacy leakage of language models (LMs) Instead of only reporting DP parameters, PrivLM-Bench sheds light on the neglected inference data privacy during actual usage. We conduct extensive experiments on three datasets of GLUE for mainstream LMs.
  arXiv  Detail & Related papers  (2023-11-07T14:55:52Z)
• Privacy-Preserving Prompt Tuning for Large Language Model Services [16.589104544849743]
  We propose a framework that provides privacy guarantees for Large Language Models (LLMs) services. textscrapt adopts a local privacy setting, allowing users to privatize their data locally with local differential privacy. Despite the simplicity of our framework, experiments show that RAPT achieves competitive performance across tasks while providing privacy guarantees against adversaries.
  arXiv  Detail & Related papers  (2023-05-10T14:41:51Z)
• Augmented Large Language Models with Parametric Knowledge Guiding [72.71468058502228]
  Large Language Models (LLMs) have significantly advanced natural language processing (NLP) with their impressive language understanding and generation capabilities. Their performance may be suboptimal for domain-specific tasks that require specialized knowledge due to limited exposure to the related data. We propose the novel Parametric Knowledge Guiding (PKG) framework, which equips LLMs with a knowledge-guiding module to access relevant knowledge.
  arXiv  Detail & Related papers  (2023-05-08T15:05:16Z)

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.