Fully Homomorphically Encrypted Deep Learning as a Service

• URL: http://arxiv.org/abs/2107.12997v1
• Date: Mon, 26 Jul 2021 20:17:48 GMT
• Title: Fully Homomorphically Encrypted Deep Learning as a Service
• Abstract summary: Fully Homomorphic Encryption (FHE) is a relatively recent advancement in the field of privacy-preserving technologies. This project investigates, derives, and proves how FHE with deep learning can be used at scale, with relatively low time complexity. We discuss how this could have an impact on the future of data privacy and how it can enable data sharing across various actors in the agri-food supply chain.
• Score: 4.082216579462797
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Fully Homomorphic Encryption (FHE) is a relatively recent advancement in the field of privacy-preserving technologies. FHE allows for the arbitrary depth computation of both addition and multiplication, and thus the application of abelian/polynomial equations, like those found in deep learning algorithms. This project investigates, derives, and proves how FHE with deep learning can be used at scale, with relatively low time complexity, the problems that such a system incurs, and mitigations/solutions for such problems. In addition, we discuss how this could have an impact on the future of data privacy and how it can enable data sharing across various actors in the agri-food supply chain, hence allowing the development of machine learning-based systems. Finally, we find that although FHE incurs a high spatial complexity cost, the time complexity is within expected reasonable bounds, while allowing for absolutely private predictions to be made, in our case for milk yield prediction.

Related papers

• Learning with Simulators: No Regret in a Computationally Bounded World [65.78002253798827]
  We introduce the framework of simulatable processes, where the learner has access to a simulator that approximates the distribution generating the data.<n>We show that we can recover the same learning guarantees as in the classical setting with independent data, namely, error bounds that depend on the VC.
  arXiv  Detail & Related papers  (2026-06-11T17:02:24Z)
• Preserving Data Privacy in Learning Causal Structure with Fully Homomorphic Encryption [30.9155633862197]
  We propose a method based on fully homomorphic encryption (FHE) that performs calculations on ciphertexts.<n>Our method achieves high consistency and comparable causal structure with the version in the datasets tested.
  arXiv  Detail & Related papers  (2026-06-03T17:33:14Z)
• Learning Intersections of Two Margin Halfspaces under Factorizable Distributions [56.51474048985742]
  Learning intersections of halfspaces is a central problem in Computational Learning Theory.<n>Even for just two halfspaces, it remains a major open question whether learning is possible in time.<n>We introduce a novel algorithm that provably circumvents the CSQ hardness barrier.
  arXiv  Detail & Related papers  (2025-11-13T00:28:24Z)
• Secure numerical simulations using fully homomorphic encryption [2.923600136516929]
  Data privacy is a significant concern when using numerical simulations for sensitive information like medical, financial, or engineering data. Fully homomorphic encryption (FHE) offers a promising solution for achieving data privacy by enabling secure computations directly on encrypted data. We show that cryptographically secure numerical simulations are possible, but that careful consideration must be given to the computational overhead and the numerical errors introduced by using FHE.
  arXiv  Detail & Related papers  (2024-10-29T07:47:10Z)
• Privacy-aware Berrut Approximated Coded Computing for Federated Learning [1.2084539012992408]
  We propose a solution to guarantee privacy in Federated Learning schemes. Our proposal is based on the Berrut Approximated Coded Computing, adapted to a Secret Sharing configuration.
  arXiv  Detail & Related papers  (2024-05-02T20:03:13Z)
• Limitations of Deep Learning for Inverse Problems on Digital Hardware [65.26723285209853]
  We analyze what actually can be computed on current hardware platforms modeled as Turing machines. We prove that finite-dimensional inverse problems are not Banach-Mazur computable for small relaxation parameters.
  arXiv  Detail & Related papers  (2022-02-28T00:20:12Z)
• Quantum Heterogeneous Distributed Deep Learning Architectures: Models, Discussions, and Applications [13.241451755566365]
  Quantum deep learning (QDL) and distributed deep learning (DDL) are emerging to complement existing deep learning methods. QDL takes computational gains by replacing deep learning computations on local devices and servers with quantum deep learning. It can increase data security by using a quantum secure communication protocol between the server and the client.
  arXiv  Detail & Related papers  (2022-02-19T12:59:11Z)
• Provable Reinforcement Learning with a Short-Term Memory [68.00677878812908]
  We study a new subclass of POMDPs, whose latent states can be decoded by the most recent history of a short length $m$. In particular, in the rich-observation setting, we develop new algorithms using a novel "moment matching" approach with a sample complexity that scales exponentially. Our results show that a short-term memory suffices for reinforcement learning in these environments.
  arXiv  Detail & Related papers  (2022-02-08T16:39:57Z)
• SoK: Privacy-preserving Deep Learning with Homomorphic Encryption [2.9069679115858755]
  homomorphic encryption (HE) can be performed on encrypted data without revealing its content. We take an in-depth look at approaches that combine neural networks with HE for privacy preservation. We find numerous challenges to HE based privacy-preserving deep learning such as computational overhead, usability, and limitations posed by the encryption schemes.
  arXiv  Detail & Related papers  (2021-12-23T22:03:27Z)
• Synthetic Data: Opening the data floodgates to enable faster, more directed development of machine learning methods [96.92041573661407]
  Many ground-breaking advancements in machine learning can be attributed to the availability of a large volume of rich data. Many large-scale datasets are highly sensitive, such as healthcare data, and are not widely available to the machine learning community. Generating synthetic data with privacy guarantees provides one such solution.
  arXiv  Detail & Related papers  (2020-12-08T17:26:10Z)
• A Survey on Large-scale Machine Learning [67.6997613600942]
  Machine learning can provide deep insights into data, allowing machines to make high-quality predictions. Most sophisticated machine learning approaches suffer from huge time costs when operating on large-scale data. Large-scale Machine Learning aims to learn patterns from big data with comparable performance efficiently.
  arXiv  Detail & Related papers  (2020-08-10T06:07:52Z)
• Sample-Efficient Reinforcement Learning of Undercomplete POMDPs [91.40308354344505]
  This work shows that these hardness barriers do not preclude efficient reinforcement learning for rich and interesting subclasses of Partially Observable Decision Processes (POMDPs) We present a sample-efficient algorithm, OOM-UCB, for episodic finite undercomplete POMDPs, where the number of observations is larger than the number of latent states and where exploration is essential for learning, thus distinguishing our results from prior works.
  arXiv  Detail & Related papers  (2020-06-22T17:58:54Z)
• Faster Secure Data Mining via Distributed Homomorphic Encryption [108.77460689459247]
  Homomorphic Encryption (HE) is receiving more and more attention recently for its capability to do computations over the encrypted field. We propose a novel general distributed HE-based data mining framework towards one step of solving the scaling problem. We verify the efficiency and effectiveness of our new framework by testing over various data mining algorithms and benchmark data-sets.
  arXiv  Detail & Related papers  (2020-06-17T18:14:30Z)
• Secure Sum Outperforms Homomorphic Encryption in (Current) Collaborative Deep Learning [7.690774882108066]
  We discuss methods for training neural networks on the joint data of different data owners, that keep each party's input confidential. We show that a less complex and computationally less expensive secure sum protocol exhibits superior properties in terms of both collusion-resistance and runtime.
  arXiv  Detail & Related papers  (2020-06-02T23:03:32Z)

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.