mlsanityData to 7 Oct 2026

Zero-Knowledge Proof-based Verifiable Decentralized Machine Learning in Communication Network: A Comprehensive Survey

arXiv 2310.14848 ↗First posted 23 Oct 2023cs.LG cs.CRcited by 18

Not on the map. Why?

Abstract (arXiv)

Over recent decades, machine learning has significantly advanced network communication, enabling improved decision-making, user behavior analysis, and fault detection. Decentralized approaches, where participants exchange computation results instead of raw private data, mitigate these risks but introduce challenges related to trust and verifiability. A critical issue arises: How can one ensure the integrity and validity of computation results shared by other participants? Existing survey articles predominantly address security and privacy concerns in decentralized machine learning, whereas this survey uniquely highlights the emerging issue of verifiability. Recognizing the critical role of zero-knowledge proofs in ensuring verifiability, we present a comprehensive review of Zero-Knowledge Proof-based Verifiable Machine Learning (ZKP-VML). To clarify the research problem, we present a definition of ZKP-VML consisting of four algorithms, along with several corresponding key security properties. Besides, we provide an overview of the current research landscape by systematically organizing the research timeline and categorizing existing schemes based on their security properties. Furthermore, through an in-depth analysis of each existing scheme, we summarize their technical contributions and optimization strategies, aiming to uncover common design principles underlying ZKP-VML schemes. Building on the reviews and analysis presented, we identify current research challenges and suggest future research directions. To the best of our knowledge, this is the most comprehensive survey to date on verifiable decentralized machine learning and ZKP-VML.

Key facts. Cited by 18 papers in the map (data through 7 Oct 2026). Builds on 54 of its 204 references that are in the map. First posted on arXiv 23 Oct 2023.

Builds on

54 of 204 references.

References · 54

  1. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,267
  2. 2016Communication-Efficient Learning of Deep Networks from Decentralized Datacited by 7,592
  3. 2017Towards Deep Learning Models Resistant to Adversarial Attackscited by 6,326
  4. 2018MobileNetV2: Inverted Residuals and Linear Bottleneckscited by 4,773
  5. 2019DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lightercited by 4,243
  6. 2016Deep Learning with Differential Privacycited by 2,682
  7. 2016Equality of Opportunity in Supervised Learningcited by 2,000
  8. 2017Quantization and Training of Neural Networks for Efficient Integer-Arithmetic-Only Inferencecited by 1,548
  9. 2021A Survey of Quantization Methods for Efficient Neural Network Inferencecited by 798
  10. 2018How To Backdoor Federated Learningcited by 745
  11. 2016TensorFlow: Large-Scale Machine Learning on Heterogeneous Distributed Systemscited by 660
  12. 2018Fine-Pruning: Defending Against Backdooring Attacks on Deep Neural Networkscited by 550
38 more
  1. 2018Measuring the Intrinsic Dimension of Objective Landscapescited by 364
  2. 2020FLTrust: Byzantine-robust Federated Learning via Trust Bootstrappingcited by 330
  3. 2019Robust Aggregation for Federated Learningcited by 314
  4. 2020Amnesiac Machine Learningcited by 305
  5. 2017Certified Defenses for Data Poisoning Attackscited by 288
  6. 2014Caffe: Convolutional Architecture for Fast Feature Embeddingcited by 287
  7. 2019Can You Really Backdoor Federated Learning?cited by 250
  8. 2021Machine Unlearning of Features and Labelscited by 223
  9. 2017A Survey on Homomorphic Encryption Schemes: Theory and Implementationcited by 154
  10. 2016An Analysis of Deep Neural Network Models for Practical Applicationscited by 114
  11. 2015Fast Algorithms for Convolutional Neural Networkscited by 102
  12. 2020Byzantine-Resilient Secure Federated Learningcited by 93
  13. 2020Data Poisoning Attacks on Federated Machine Learningcited by 58
  14. 2019Zeno++: Robust Fully Asynchronous SGDcited by 53
  15. 2022Robust Semantic Communications with Masked VQ-VAE Enabled Codebookcited by 53
  16. 2017SafetyNets: Verifiable Execution of Deep Neural Networks on an Untrusted Cloudcited by 50
  17. 2016Compression of Neural Machine Translation Models via Pruningcited by 43
  18. 2017Prio: Private, Robust, and Scalable Computation of Aggregate Statisticscited by 35
  19. 2021FedIPR: Ownership Verification for Federated Deep Neural Network Modelscited by 33
  20. 2022Scaling up Trustless DNN Inference with Zero-Knowledge Proofscited by 30
  21. 2019VeriML: Enabling Integrity Assurances and Fair Payments for Machine Learning as a Servicecited by 26
  22. 2021EIFFeL: Ensuring Integrity for Federated Learningcited by 26
  23. 2022Verifiable and Provably Secure Machine Unlearningcited by 24
  24. 2021RoFL: Robustness of Secure Federated Learningcited by 23
  25. 2020An Accurate, Scalable and Verifiable Protocol for Federated Differentially Private Averagingcited by 20
  26. 2022pvCNN: Privacy-Preserving and Verifiable Convolutional Neural Network Testingcited by 20
  27. 2021Fairness, Integrity, and Privacy in a Scalable Blockchain-based Federated Learning Systemcited by 16
  28. 2023Blockchain-aided Secure Semantic Communication for AI-Generated Content in Metaversecited by 15
  29. 2022Preserving Privacy and Security in Federated Learningcited by 13
  30. 2022Towards Verifiable Federated Learningcited by 11
  31. 2022Encrypted Semantic Communication Using Adversarial Training for Privacy Preservingcited by 10
  32. 2022ezDPS: An Efficient and Zero-Knowledge Machine Learning Inference Pipelinecited by 10
  33. 2023Zero-Knowledge Proof-based Practical Federated Learning on Blockchaincited by 9
  34. 2023FedZKP: Federated Model Ownership Verification with Zero-knowledge Proofcited by 9
  35. 2019Drynx: Decentralized, Secure, Verifiable System for Statistical Queries and Machine Learning on Distributed Datasetscited by 8
  36. 2023Secure Federated Learning against Model Poisoning Attacks via Client Filteringcited by 8
  37. 2023Verifiable Fairness: Privacy-preserving Computation of Fairness for Machine Learning Systemscited by 7
  38. 2022zPROBE: Zero Peek Robustness Checks for Federated Learningcited by 6

50 most cited of 54 All 54 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 1; 2024: 5; 2025: 5; 2026: 7.

18 papers.

Sort:

By area:

  1. 2025A Survey of Zero-Knowledge Proof Based Verifiable Machine Learningcited by 21
  2. 2024Game of Coding: Sybil Resistant Decentralized Machine Learning with Minimal Trust Assumptioncited by 5
  3. 2026The Rise of Sparse Mixture-of-Experts: A Survey from Algorithmic Foundations to Decentralized Architectures and Vertical Domain Applicationscited by 2
  4. 2024FTSmartAudit: A Knowledge Distillation-Enhanced Framework for Automated Smart Contract Auditing Using Fine-Tuned LLMscited by 1
  5. 2025ZTFed-MAS2S: A Zero-Trust Federated Learning Framework with Verifiable Privacy and Trust-Aware Aggregation for Wind Power Data Imputationcited by 1
  6. 2026Combating Knowledge Corruption in Agent Systems: A Byzantine-Tolerant Secure Collaborative RAG Frameworkcited by 1
  7. 2023Decentralized Energy Marketplace via NFTs and AI-based Agentscited by 0
  8. 2024Privacy-Preserving UCB Decision Process Verification via zk-SNARKscited by 0
  9. 2024Privacy-Preserving and Trustworthy Deep Learning for Medical Imagingcited by 0
  10. 2024SoK: Verifiable Cross-Silo FLcited by 0
  11. 2025DSperse: A Framework for Targeted Verification in Zero-Knowledge Machine Learningcited by 0
  12. 2025Towards Verifiable Federated Unlearning: Framework, Challenges, and The Road Aheadcited by 0
6 more
  1. 2025On the Detectability of Active Gradient Inversion Attacks in Federated Learningcited by 0
  2. 2026VeriX-Anon: A Multi-Layered Framework for Mathematically Verifiable Outsourced Target-Driven Data Anonymizationcited by 0
  3. 2026AME: A Multi-Type Contributor Attribution Framework in Generative AI Marketscited by 0
  4. 2026Certification of Machine Learning Models via Directional Sharpnesscited by 0
  5. 2026Privacy-Preserving and Verifiable Approximate Distributed Coded Computingcited by 0
  6. 2026Physics-Attested Federated Learning: Securing Collaborative Anomaly Detection in Critical Water Infrastructurecited by 0