ConfusionPrompt: Practical Private Inference for Online Large Language Models

• URL: http://arxiv.org/abs/2401.00870v4
• Date: Wed, 06 Nov 2024 02:55:01 GMT
• Title: ConfusionPrompt: Practical Private Inference for Online Large Language Models
• Authors: Peihua Mai, Youjia Yang, Ran Yan, Rui Ye, Yan Pang,
• Abstract summary: 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.
• Score: 3.8134804426693094
• License:
• Abstract: State-of-the-art large language models (LLMs) are typically deployed as online services, requiring users to transmit detailed prompts to cloud servers. This raises significant privacy concerns. In response, we introduce ConfusionPrompt, a novel framework for private LLM inference that protects user privacy by: (i) decomposing the original prompt into smaller sub-prompts, and (ii) generating pseudo-prompts alongside the genuine sub-prompts, which are then sent to the LLM. The server responses are later recomposed by the user to reconstruct the final output. This approach offers key advantages over previous LLM privacy protection methods: (i) it integrates seamlessly with existing black-box LLMs, and (ii) it delivers a significantly improved privacy-utility trade-off compared to existing text perturbation methods. We also develop a $(\lambda, \mu, \rho)$-privacy model to formulate the requirements for a privacy-preserving group of prompts and provide a complexity analysis to justify the role of prompt decomposition. Our empirical evaluation shows that ConfusionPrompt achieves significantly higher utility than local inference methods using open-source models and perturbation-based techniques, while also reducing memory consumption compared to open-source LLMs.

Related papers

• Boosting Private Domain Understanding of Efficient MLLMs: A Tuning-free, Adaptive, Universal Prompt Optimization Framework [60.26747209785186]
  multimodal large language models (EMLLMs) reduce model size and computational costs and are often deployed on resource-constrained devices. Existing open-sourceLMs rarely have access to private domain-specific data during the pre-training process. We propose a tuntextbfunderlineIng-free, atextbfunderlineDaptivtextbfunderlineE, universtextbfunderlineAL textbfunderlinePrompt Optimization Framework.
  arXiv  Detail & Related papers  (2024-12-27T15:21:17Z)
• The Early Bird Catches the Leak: Unveiling Timing Side Channels in LLM Serving Systems [26.528288876732617]
  A set of new timing side channels can be exploited to infer confidential system prompts and those issued by other users. These vulnerabilities echo security challenges observed in traditional computing systems. We propose a token-by-token search algorithm to efficiently recover shared prompt prefixes in the caches.
  arXiv  Detail & Related papers  (2024-09-30T06:55:00Z)
• Confidential Prompting: Protecting User Prompts from Cloud LLM Providers [0.688204255655161]
  Our work tackles the challenge of securing user inputs in cloud-hosted large language model (LLM) serving. We introduce secure multi-party decoding (SMD), which leverages confidential computing to confine user prompts to a trusted execution environment. We demonstrate that our approach preserves both prompt confidentiality and LLM serving efficiency.
  arXiv  Detail & Related papers  (2024-09-27T20:32:42Z)
• Prompt Tuning as User Inherent Profile Inference Machine [53.78398656789463]
  We propose UserIP-Tuning, which uses prompt-tuning to infer user profiles. A profile quantization codebook bridges the modality gap by profile embeddings into collaborative IDs. Experiments on four public datasets show that UserIP-Tuning outperforms state-of-the-art recommendation algorithms.
  arXiv  Detail & Related papers  (2024-08-13T02:25:46Z)
• Robust Utility-Preserving Text Anonymization Based on Large Language Models [80.5266278002083]
  Text anonymization is crucial for sharing sensitive data while maintaining privacy. Existing techniques face the emerging challenges of re-identification attack ability of Large Language Models. This paper proposes a framework composed of three LLM-based components -- a privacy evaluator, a utility evaluator, and an optimization component.
  arXiv  Detail & Related papers  (2024-07-16T14:28:56Z)
• 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)
• Personalized LLM Response Generation with Parameterized Memory Injection [17.48756504658829]
  Large Language Models (LLMs) have exhibited remarkable proficiency in comprehending and generating natural language. personalized LLM response generation holds the potential to offer substantial benefits for individuals in critical areas such as medical.
  arXiv  Detail & Related papers  (2024-04-04T16:20:34Z)
• 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)
• Language Models as Black-Box Optimizers for Vision-Language Models [62.80817942316398]
  Vision-language models (VLMs) pre-trained on web-scale datasets have demonstrated remarkable capabilities on downstream tasks when fine-tuned with minimal data. We aim to develop a black-box approach to optimize VLMs through natural language prompts.
  arXiv  Detail & Related papers  (2023-09-12T04:03:41Z)
• Hide and Seek (HaS): A Lightweight Framework for Prompt Privacy Protection [6.201275002179716]
  We introduce the HaS framework, where "H(ide)" and "S(eek)" represent its two core processes: hiding private entities for anonymization and seeking private entities for de-anonymization. To quantitatively assess HaS's privacy protection performance, we propose both black-box and white-box adversarial models.
  arXiv  Detail & Related papers  (2023-09-06T14:54:11Z)
• Check Your Facts and Try Again: Improving Large Language Models with External Knowledge and Automated Feedback [127.75419038610455]
  Large language models (LLMs) are able to generate human-like, fluent responses for many downstream tasks. This paper proposes a LLM-Augmenter system, which augments a black-box LLM with a set of plug-and-play modules.
  arXiv  Detail & Related papers  (2023-02-24T18:48:43Z)

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.