mlsanityData to 14 Oct 2026

Privacy-Preserving UCB Decision Process Verification via zk-SNARKs

arXiv 2404.12186 ↗First posted 18 Apr 2024cs.LG cs.CRcited by 0

Not on the map. Why?

Abstract (arXiv)

With the increasingly widespread application of machine learning, how to strike a balance between protecting the privacy of data and algorithm parameters and ensuring the verifiability of machine learning has always been a challenge. This study explores the intersection of reinforcement learning and data privacy, specifically addressing the Multi-Armed Bandit (MAB) problem with the Upper Confidence Bound (UCB) algorithm. We introduce zkUCB, an innovative algorithm that employs the Zero-Knowledge Succinct Non-Interactive Argument of Knowledge (zk-SNARKs) to enhance UCB. zkUCB is carefully designed to safeguard the confidentiality of training data and algorithmic parameters, ensuring transparent UCB decision-making. Experiments highlight zkUCB's superior performance, attributing its enhanced reward to judicious quantization bit usage that reduces information entropy in the decision-making process. zkUCB's proof size and verification time scale linearly with the execution steps of zkUCB. This showcases zkUCB's adept balance between data security and operational efficiency. This approach contributes significantly to the ongoing discourse on reinforcing data privacy in complex decision-making processes, offering a promising solution for privacy-sensitive applications.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 11 of its 27 references that are in the map. First posted on arXiv 18 Apr 2024.

Builds on

11 of 27 references.

References · 11

  1. 2020Deep Reinforcement Learning for Autonomous Driving: A Surveycited by 721
  2. 2019Reinforcement Learning in Healthcare: A Surveycited by 310
  3. 2021Reinforcement learning based recommender systems: A surveycited by 188
  4. 2019Achieving Fairness in the Stochastic Multi-armed Bandit Problemcited by 78
  5. 2017SafetyNets: Verifiable Execution of Deep Neural Networks on an Untrusted Cloudcited by 50
  6. 2019On Multi-Armed Bandit Designs for Dose-Finding Clinical Trialscited by 32
  7. 2019VeriML: Enabling Integrity Assurances and Fair Payments for Machine Learning as a Servicecited by 28
  8. 2022When Privacy Meets Partial Information: A Refined Analysis of Differentially Private Banditscited by 28
  9. 2023Zero-Knowledge Proof-based Verifiable Decentralized Machine Learning in Communication Network: A Comprehensive Surveycited by 18
  10. 2020Offline Contextual Multi-armed Bandits for Mobile Health Interventions: A Case Study on Emotion Regulationcited by 13
  11. 2022A Review of zk-SNARKscited by 8

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2024Near-Optimal Reinforcement Learning with Shuffle Differential Privacy
  2. 2025Efficient Implementation of Reinforcement Learning over Homomorphic Encryption
  3. 2026Privacy Preserving Reinforcement Learning with One-Sided Feedback
  4. 2022SoK: Let the Privacy Games Begin! A Unified Treatment of Data Inference Privacy in Machine Learning
  5. 2025Towards Optimal Differentially Private Regret Bounds in Linear MDPs
  6. 2026Privacy-Preserving Reinforcement Learning from Human Feedback via Decoupled Reward Modeling
  7. 2025KL-regularization Itself is Differentially Private in Bandits and RLHF
  8. 2022Offline Reinforcement Learning with Differential Privacy