Secure Summation via Subset Sums: A New Primitive for Privacy-Preserving Distributed Machine Learning

• URL: http://arxiv.org/abs/1906.11993v2
• Date: Mon, 19 Jun 2023 18:23:56 GMT
• Title: Secure Summation via Subset Sums: A New Primitive for Privacy-Preserving Distributed Machine Learning
• Authors: Valentin Hartmann, Robert West
• Abstract summary: Summation is an important primitive for computing means, counts or mini-batch gradients. In many cases, the data is privacy-sensitive and cannot be collected on a central server. Existing solutions for distributed summation with computational privacy guarantees make trust or connection assumptions that might not be fulfilled in real world settings. We propose Secure Summation via Subset Sums (S5), a method for distributed summation that works in the presence of a malicious server and only two honest clients.
• Score: 15.275126264550943
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: For population studies or for the training of complex machine learning models, it is often required to gather data from different actors. In these applications, summation is an important primitive: for computing means, counts or mini-batch gradients. In many cases, the data is privacy-sensitive and therefore cannot be collected on a central server. Hence the summation needs to be performed in a distributed and privacy-preserving way. Existing solutions for distributed summation with computational privacy guarantees make trust or connection assumptions - e.g., the existence of a trusted server or peer-to-peer connections between clients - that might not be fulfilled in real world settings. Motivated by these challenges, we propose Secure Summation via Subset Sums (S5), a method for distributed summation that works in the presence of a malicious server and only two honest clients, and without the need for peer-to-peer connections between clients. S5 adds zero-sum noise to clients' messages and shuffles them before sending them to the aggregating server. Our main contribution is a proof that this scheme yields a computational privacy guarantee based on the multidimensional subset sum problem. Our analysis of this problem may be of independent interest for other privacy and cryptography applications.

Related papers

• CURE: Privacy-Preserving Split Learning Done Right [1.388112207221632]
  Homomorphic encryption (HE)-based solutions exist for this scenario but often impose prohibitive computational burdens. CURE is a novel system that encrypts only the server side of the model and the data. We demonstrate CURE can achieve similar accuracy to plaintext SL while being 16x more efficient in terms of the runtime.
  arXiv  Detail & Related papers  (2024-07-12T04:10:19Z)
• 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)
• Client-specific Property Inference against Secure Aggregation in Federated Learning [52.8564467292226]
  Federated learning has become a widely used paradigm for collaboratively training a common model among different participants. Many attacks have shown that it is still possible to infer sensitive information such as membership, property, or outright reconstruction of participant data. We show that simple linear models can effectively capture client-specific properties only from the aggregated model updates.
  arXiv  Detail & Related papers  (2023-03-07T14:11:01Z)
• Scalable Collaborative Learning via Representation Sharing [53.047460465980144]
  Federated learning (FL) and Split Learning (SL) are two frameworks that enable collaborative learning while keeping the data private (on device) In FL, each data holder trains a model locally and releases it to a central server for aggregation. In SL, the clients must release individual cut-layer activations (smashed data) to the server and wait for its response (during both inference and back propagation). In this work, we present a novel approach for privacy-preserving machine learning, where the clients collaborate via online knowledge distillation using a contrastive loss.
  arXiv  Detail & Related papers  (2022-11-20T10:49:22Z)
• Smooth Anonymity for Sparse Graphs [69.1048938123063]
  differential privacy has emerged as the gold standard of privacy, however, when it comes to sharing sparse datasets. In this work, we consider a variation of $k$-anonymity, which we call smooth-$k$-anonymity, and design simple large-scale algorithms that efficiently provide smooth-$k$-anonymity.
  arXiv  Detail & Related papers  (2022-07-13T17:09:25Z)
• Secure Distributed/Federated Learning: Prediction-Privacy Trade-Off for Multi-Agent System [4.190359509901197]
  In the big data era, performing inference within the distributed and federated learning (DL and FL) frameworks, the central server needs to process a large amount of data. Considering the decentralized computing topology, privacy has become a first-class concern. We study the textitprivacy-aware server to multi-agent assignment problem subject to information processing constraints associated with each agent.
  arXiv  Detail & Related papers  (2022-04-24T19:19:20Z)
• Federated Multi-Target Domain Adaptation [99.93375364579484]
  Federated learning methods enable us to train machine learning models on distributed user data while preserving its privacy. We consider a more practical scenario where the distributed client data is unlabeled, and a centralized labeled dataset is available on the server. We propose an effective DualAdapt method to address the new challenges.
  arXiv  Detail & Related papers  (2021-08-17T17:53:05Z)
• Differentially Private Secure Multi-Party Computation for Federated Learning in Financial Applications [5.50791468454604]
  Federated learning enables a population of clients, working with a trusted server, to collaboratively learn a shared machine learning model. This reduces the risk of exposing sensitive data, but it is still possible to reverse engineer information about a client's private data set from communicated model parameters. We present a privacy-preserving federated learning protocol to a non-specialist audience, demonstrate it using logistic regression on a real-world credit card fraud data set, and evaluate it using an open-source simulation platform.
  arXiv  Detail & Related papers  (2020-10-12T17:16:27Z)
• Privacy Amplification via Random Check-Ins [38.72327434015975]
  Differentially Private Gradient Descent (DP-SGD) forms a fundamental building block in many applications for learning over sensitive data. In this paper, we focus on conducting iterative methods like DP-SGD in the setting of federated learning (FL) wherein the data is distributed among many devices (clients) Our main contribution is the emphrandom check-in distributed protocol, which crucially relies only on randomized participation decisions made locally and independently by each client.
  arXiv  Detail & Related papers  (2020-07-13T18:14:09Z)
• Corella: A Private Multi Server Learning Approach based on Correlated Queries [30.3330177204504]
  We propose $textitCorella$ as an alternative approach to protect the privacy of data. The proposed scheme relies on a cluster of servers, where at most $T in mathbbN$ of them may collude, each running a learning model. The variance of the noise is set to be large enough to make the information leakage to any subset of up to $T$ servers information-theoretically negligible.
  arXiv  Detail & Related papers  (2020-03-26T17:44:00Z)
• 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.