Challenges
Datasets
Workspaces
Papers
Discussions
Leaderboard
Log inSign up
Challenges
Datasets
Workspaces
Papers
Discussions
Leaderboard
Blog
Job Board
Q3AS

© 2026 Aqora Quantum S.A.S.

TermsPrivacyLegal Notice

arXiv:2506.00518 · Lecture notes in computer science

Robust and Verifiable MPC with Applications to Linear Machine Learning Inference

Tzu-Shen Wang, Jimmy Dani, Juan A. Garay, Soamar Homsi, Nitesh Saxena

Published Nov 23, 2025• 1 citation
arXivHTMLPDF
DOI
10.1007/978-3-032-10759-6_6

Related papers

Quantum Bayesian Inference for Statistical Machine Learning

Jincheng Zhang

Quantum Bayesian Inference (QBI) presents a novel approach to statistical machine learning, utilizing the principles of quantum mechanics to enhance the accuracy and robustness of models, particularly when dealing with high-dimensional data and complex Bayesian frameworks. This paper introduces a quantum algorithm designed to efficiently estimate the posterior distribution of parameters in a Bayesian model through the application of quantum superposition and entanglement, aiming to overcome the limitations of classical methods. We explore the potential of this paradigm shift to deliver exponential speedups in inference tasks, offering a compelling path towards more accurate and reliable statistical machine learning algorithms.

•Aug 29, 2026•0 citations

Information-Theoretic Robust MPC Protocols

Ronald Cramer, Ivan Damgård, Jesper Buus Nielsen

Cambridge University Press eBooks•Jun 30, 2015•0 citations

Linear Overhead Optimally-Resilient Robust MPC Using Preprocessing

Ashish Choudhury, Emmanuela Orsini, Arpita Patra +1 more

Lecture notes in computer science•Jan 1, 2016•4 citations

Title: Quantum-Inspired Non-Linearity in Machine Learning

Jincheng Zhang

Quantum-inspired non-linearities offer a promising avenue for enhancing the robustness and generalization of machine learning models. This paper explores the potential of incorporating quantum-like phenomena into learning algorithms to mitigate noise and facilitate adaptation. We propose a novel framework that leverages superposition and entanglement to create models less susceptible to fluctuations in input data, ultimately improving predictive performance. The core mechanism focuses on introducing these quantum-inspired elements to promote stability and resilience in model training and inference. The research aims to address limitations of current machine learning approaches by introducing a fundamentally different method for handling uncertainty and exploring robust solutions. We present preliminary results demonstrating the effectiveness of this framework in several benchmark datasets, highlighting its potential for advancing the field.

•Sep 6, 2026•0 citations

Adaptively Secure MPC with Sublinear Communication Complexity

Ran Cohen, Abhi A. Shelat, Daniel Wichs

Lecture notes in computer science•Jan 1, 2019•26 citations

Smart intelligent control application using quantum computation and machine learning

Saroj Kumar Nanda, S. Arockia Panimalar, Sreekanth Rallapalli +3 more

In terms of service quality for transportation, security, robotics, healthcare, power, finance, etc., machine learning (ML) is effectively disrupting and modernizing cities. Even with their overwhelming success, machine learning (ML) algorithms still require significant computational work with fast computer hardware in order to handle model complexity and guarantees that result in effective, dependable, and robust solutions. Regarding cybersecurity and digital protection, quantum computing (QC) is a formidable contender to assist machine learning (ML) systems achieve optimal performance. The goal of this research is to provide the quantum Adaptive Neuro-fuzzy Inference System (QANFIS) model for smart control application distributed denial of service attack detection. The usefulness of our proposed model is demonstrated by evaluating it against an actual dataset of denial of service attack incidents. Lastly, various unresolved problems and difficulties with fitting ML with QC are discussed along with the findings.

CRC Press eBooks•Jan 29, 2025•0 citations
Quantum Bayesian Inference (QBI) presents a novel approach to statistical machine learning, utilizing the principles of quantum mechanics to enhance the accuracy and robustness of models, particularly when dealing with high-dimensional data and complex Bayesian frameworks. This paper introduces a quantum algorithm designed to efficiently estimate the posterior distribution of parameters in a Bayesian model through the application of quantum superposition and entanglement, aiming to overcome the limitations of classical methods. We explore the potential of this paradigm shift to deliver exponential speedups in inference tasks, offering a compelling path towards more accurate and reliable statistical machine learning algorithms.
Quantum-inspired non-linearities offer a promising avenue for enhancing the robustness and generalization of machine learning models. This paper explores the potential of incorporating quantum-like phenomena into learning algorithms to mitigate noise and facilitate adaptation. We propose a novel framework that leverages superposition and entanglement to create models less susceptible to fluctuations in input data, ultimately improving predictive performance. The core mechanism focuses on introducing these quantum-inspired elements to promote stability and resilience in model training and inference. The research aims to address limitations of current machine learning approaches by introducing a fundamentally different method for handling uncertainty and exploring robust solutions. We present preliminary results demonstrating the effectiveness of this framework in several benchmark datasets, highlighting its potential for advancing the field.
In terms of service quality for transportation, security, robotics, healthcare, power, finance, etc., machine learning (ML) is effectively disrupting and modernizing cities. Even with their overwhelming success, machine learning (ML) algorithms still require significant computational work with fast computer hardware in order to handle model complexity and guarantees that result in effective, dependable, and robust solutions. Regarding cybersecurity and digital protection, quantum computing (QC) is a formidable contender to assist machine learning (ML) systems achieve optimal performance. The goal of this research is to provide the quantum Adaptive Neuro-fuzzy Inference System (QANFIS) model for smart control application distributed denial of service attack detection. The usefulness of our proposed model is demonstrated by evaluating it against an actual dataset of denial of service attack incidents. Lastly, various unresolved problems and difficulties with fitting ML with QC are discussed along with the findings.