Privacy-Preserving Verifiable Neural Network Inference Service

• URL: http://arxiv.org/abs/2411.07468v2
• Date: Wed, 13 Nov 2024 03:07:36 GMT
• Title: Privacy-Preserving Verifiable Neural Network Inference Service
• Authors: Arman Riasi, Jorge Guajardo, Thang Hoang,
• Abstract summary: We develop a privacy-preserving and verifiable CNN inference scheme that preserves privacy for client data samples. vPIN achieves high efficiency in terms of proof size, while providing client data privacy guarantees and provable verifiability.
• Score: 4.131956503199438
• License:
• Abstract: Machine learning has revolutionized data analysis and pattern recognition, but its resource-intensive training has limited accessibility. Machine Learning as a Service (MLaaS) simplifies this by enabling users to delegate their data samples to an MLaaS provider and obtain the inference result using a pre-trained model. Despite its convenience, leveraging MLaaS poses significant privacy and reliability concerns to the client. Specifically, sensitive information from the client inquiry data can be leaked to an adversarial MLaaS provider. Meanwhile, the lack of a verifiability guarantee can potentially result in biased inference results or even unfair payment issues. While existing trustworthy machine learning techniques, such as those relying on verifiable computation or secure computation, offer solutions to privacy and reliability concerns, they fall short of simultaneously protecting the privacy of client data and providing provable inference verifiability. In this paper, we propose vPIN, a privacy-preserving and verifiable CNN inference scheme that preserves privacy for client data samples while ensuring verifiability for the inference. vPIN makes use of partial homomorphic encryption and commit-and-prove succinct non-interactive argument of knowledge techniques to achieve desirable security properties. In vPIN, we develop various optimization techniques to minimize the proving circuit for homomorphic inference evaluation thereby, improving the efficiency and performance of our technique. We fully implemented and evaluated our vPIN scheme on standard datasets (e.g., MNIST, CIFAR-10). Our experimental results show that vPIN achieves high efficiency in terms of proving time, verification time, and proof size, while providing client data privacy guarantees and provable verifiability.

Related papers

• Federated Face Forgery Detection Learning with Personalized Representation [63.90408023506508]
  Deep generator technology can produce high-quality fake videos that are indistinguishable, posing a serious social threat. Traditional forgery detection methods directly centralized training on data. The paper proposes a novel federated face forgery detection learning with personalized representation.
  arXiv  Detail & Related papers  (2024-06-17T02:20:30Z)
• Certifiably Byzantine-Robust Federated Conformal Prediction [49.23374238798428]
  We introduce a novel framework Rob-FCP, which executes robust federated conformal prediction effectively countering malicious clients. We empirically demonstrate the robustness of Rob-FCP against diverse proportions of malicious clients under a variety of Byzantine attacks.
  arXiv  Detail & Related papers  (2024-06-04T04:43:30Z)
• Secure and Verifiable Data Collaboration with Low-Cost Zero-Knowledge Proofs [30.260427020479536]
  In this paper, we propose a novel and highly efficient solution RiseFL for secure and verifiable data collaboration. Firstly, we devise a probabilistic integrity check method that significantly reduces the cost of ZKP generation and verification. Thirdly, we design a hybrid commitment scheme to satisfy Byzantine robustness with improved performance.
  arXiv  Detail & Related papers  (2023-11-26T14:19:46Z)
• Tight Auditing of Differentially Private Machine Learning [77.38590306275877]
  For private machine learning, existing auditing mechanisms are tight. They only give tight estimates under implausible worst-case assumptions. We design an improved auditing scheme that yields tight privacy estimates for natural (not adversarially crafted) datasets.
  arXiv  Detail & Related papers  (2023-02-15T21:40:33Z)
• No Free Lunch in "Privacy for Free: How does Dataset Condensation Help Privacy" [75.98836424725437]
  New methods designed to preserve data privacy require careful scrutiny. Failure to preserve privacy is hard to detect, and yet can lead to catastrophic results when a system implementing a privacy-preserving'' method is attacked.
  arXiv  Detail & Related papers  (2022-09-29T17:50:23Z)
• ABC-FL: Anomalous and Benign client Classification in Federated Learning [0.0]
  Federated Learning is a distributed machine learning framework designed for data privacy preservation. It inherits the vulnerabilities and susceptibilities raised in deep learning techniques. It is difficult to correctly identify malicious clients due to the non-Independently and/or Identically Distributed (non-IID) data. We propose a method that detects and classifies anomalous clients from benign clients when benign ones have non-IID data.
  arXiv  Detail & Related papers  (2021-08-10T09:54:25Z)
• Efficient CNN Building Blocks for Encrypted Data [6.955451042536852]
  Homomorphic Encryption (FHE) is a promising technique to enable machine learning and inferencing. We show that operational parameters of the chosen FHE scheme have a major impact on the design of the machine learning model. Our empirical study shows that choice of aforementioned design parameters result in significant trade-offs between accuracy, security level, and computational time.
  arXiv  Detail & Related papers  (2021-01-30T21:47:23Z)
• Trustworthy AI [75.99046162669997]
  Brittleness to minor adversarial changes in the input data, ability to explain the decisions, address the bias in their training data, are some of the most prominent limitations. We propose the tutorial on Trustworthy AI to address six critical issues in enhancing user and public trust in AI systems.
  arXiv  Detail & Related papers  (2020-11-02T20:04:18Z)
• Towards Probabilistic Verification of Machine Unlearning [30.892906429582904]
  We propose a formal framework to study the design of verification mechanisms for data deletion requests. We show that our approach has minimal effect on the machine learning service's accuracy but provides high confidence verification of unlearning.
  arXiv  Detail & Related papers  (2020-03-09T16:39:46Z)
• CryptoSPN: Privacy-preserving Sum-Product Network Inference [84.88362774693914]
  We present a framework for privacy-preserving inference of sum-product networks (SPNs) CryptoSPN achieves highly efficient and accurate inference in the order of seconds for medium-sized SPNs.
  arXiv  Detail & Related papers  (2020-02-03T14:49:18Z)

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.