Inference Privacy: Properties and Mechanisms

• URL: http://arxiv.org/abs/2411.18746v1
• Date: Wed, 27 Nov 2024 20:47:28 GMT
• Title: Inference Privacy: Properties and Mechanisms
• Authors: Fengwei Tian, Ravi Tandon,
• Abstract summary: Inference Privacy (IP) can allow a user to interact with a model while providing a rigorous privacy guarantee for the users' data at inference.<n>We present two types of mechanisms for achieving IP: namely, input perturbations and output perturbations which are customizable by the users.
• Score: 8.471466670802817
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Ensuring privacy during inference stage is crucial to prevent malicious third parties from reconstructing users' private inputs from outputs of public models. Despite a large body of literature on privacy preserving learning (which ensures privacy of training data), there is no existing systematic framework to ensure the privacy of users' data during inference. Motivated by this problem, we introduce the notion of Inference Privacy (IP), which can allow a user to interact with a model (for instance, a classifier, or an AI-assisted chat-bot) while providing a rigorous privacy guarantee for the users' data at inference. We establish fundamental properties of the IP privacy notion and also contrast it with the notion of Local Differential Privacy (LDP). We then present two types of mechanisms for achieving IP: namely, input perturbations and output perturbations which are customizable by the users and can allow them to navigate the trade-off between utility and privacy. We also demonstrate the usefulness of our framework via experiments and highlight the resulting trade-offs between utility and privacy during inference.

Related papers

• Token-Level Privacy in Large Language Models [7.4143291213663955]
  We introduce dchi-stencil, a novel token-level privacy-preserving mechanism that integrates contextual and semantic information. By incorporating both semantic and contextual nuances, dchi-stencil achieves a robust balance between privacy and utility. This work highlights the potential of dchi-stencil to set a new standard for privacy-preserving NLP in modern, high-risk applications.
  arXiv  Detail & Related papers  (2025-03-05T16:27:25Z)
• On the Differential Privacy and Interactivity of Privacy Sandbox Reports [78.85958224681858]
  The Privacy Sandbox initiative from Google includes APIs for enabling privacy-preserving advertising functionalities. We provide an abstract model for analyzing the privacy of these APIs and show that they satisfy a formal DP guarantee.
  arXiv  Detail & Related papers  (2024-12-22T08:22:57Z)
• Collaborative Inference over Wireless Channels with Feature Differential Privacy [57.68286389879283]
  Collaborative inference among multiple wireless edge devices has the potential to significantly enhance Artificial Intelligence (AI) applications. transmitting extracted features poses a significant privacy risk, as sensitive personal data can be exposed during the process. We propose a novel privacy-preserving collaborative inference mechanism, wherein each edge device in the network secures the privacy of extracted features before transmitting them to a central server for inference.
  arXiv  Detail & Related papers  (2024-10-25T18:11:02Z)
• Masked Differential Privacy [64.32494202656801]
  We propose an effective approach called masked differential privacy (DP), which allows for controlling sensitive regions where differential privacy is applied. Our method operates selectively on data and allows for defining non-sensitive-temporal regions without DP application or combining differential privacy with other privacy techniques within data samples.
  arXiv  Detail & Related papers  (2024-10-22T15:22:53Z)
• 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)
• PrivacyRestore: Privacy-Preserving Inference in Large Language Models via Privacy Removal and Restoration [18.11846784025521]
  PrivacyRestore is a plug-and-play method to protect the privacy of user inputs during inference. We create three datasets, covering medical and legal domains, to evaluate the effectiveness of PrivacyRestore.
  arXiv  Detail & Related papers  (2024-06-03T14:57:39Z)
• Privacy-Preserving Language Model Inference with Instance Obfuscation [33.86459812694288]
  Language Models as a Service (LM) offers convenient access for developers and researchers to perform inference using pre-trained language models. The input data and the inference results containing private information are exposed as plaintext during the service call, leading to privacy issues. We propose Instance-Obfuscated Inference (IOI) method, which focuses on addressing the decision privacy issue of natural language understanding tasks.
  arXiv  Detail & Related papers  (2024-02-13T05:36:54Z)
• A Learning-based Declarative Privacy-Preserving Framework for Federated Data Management [23.847568516724937]
  We introduce a new privacy-preserving technique that uses a deep learning model trained using Differentially-Private Descent (DP-SGD) algorithm. We then demonstrate a novel declarative privacy-preserving workflow that allows users to specify "what private information to protect" rather than "how to protect"
  arXiv  Detail & Related papers  (2024-01-22T22:50:59Z)
• 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)
• Can Language Models be Instructed to Protect Personal Information? [30.187731765653428]
  We introduce PrivQA -- a benchmark to assess the privacy/utility trade-off when a model is instructed to protect specific categories of personal information in a simulated scenario. We find that adversaries can easily circumvent these protections with simple jailbreaking methods through textual and/or image inputs. We believe PrivQA has the potential to support the development of new models with improved privacy protections, as well as the adversarial robustness of these protections.
  arXiv  Detail & Related papers  (2023-10-03T17:30:33Z)
• Position: Considerations for Differentially Private Learning with Large-Scale Public Pretraining [75.25943383604266]
  We question whether the use of large Web-scraped datasets should be viewed as differential-privacy-preserving. We caution that publicizing these models pretrained on Web data as "private" could lead to harm and erode the public's trust in differential privacy as a meaningful definition of privacy. We conclude by discussing potential paths forward for the field of private learning, as public pretraining becomes more popular and powerful.
  arXiv  Detail & Related papers  (2022-12-13T10:41:12Z)
• How Do Input Attributes Impact the Privacy Loss in Differential Privacy? [55.492422758737575]
  We study the connection between the per-subject norm in DP neural networks and individual privacy loss. We introduce a novel metric termed the Privacy Loss-Input Susceptibility (PLIS) which allows one to apportion the subject's privacy loss to their input attributes.
  arXiv  Detail & Related papers  (2022-11-18T11:39:03Z)

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.