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

TL;DR

This survey addresses the verifiability gap in decentralized machine learning by formalizing zero-knowledge proof-based verifiable ML (ZKP-VML) and outlining a comprehensive landscape of schemes, timelines, and design principles. It introduces a formal definition of ZKP-VML, classifies existing work along technical routes and optimization strategies, and analyzes concrete schemes for integrity, fairness, aggregation, ownership, unlearning, and LLM/inference in semantic contexts. The paper highlights critical challenges—float/activation mapping, proof efficiency, and evaluability—and presents future directions spanning efficiency, real-world deployment, novel ML scenarios, and network integration. By mapping 56 schemes to a unified framework and proposing avenues for standardization and tooling, the work aims to accelerate practical, privacy-preserving verifiable ML across communication networks.

Abstract

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.

Figures (6)

• Figure 1: Real-life applications of zero-knowledge proof-based verifiable machine learning
• Figure 2: The architecture of different verifiable machine learning.
• Figure 3: The workflow of verifiable machine learning.
• Figure 4: Timeline of existing work in the field of ZKP-VML for training and inference. The dash line from scheme A to B indicates that B is shown to be more advanced than A under certain conditions by theoretical or experimental analysis. The solid line from schemes A to B indicates that B is inspired by A. For brevity, we omit the dash line from A to C, when A points to both B, C and B points to C.
• Figure 5: Timeline of existing work in the field of ZKP-VML for emerging scenarios and computations. The dash line from scheme A to B indicates that B is shown to be more advanced than A under certain conditions by theoretical or experimental analysis. The solid line from schemes A to B indicates that B is inspired by A. For brevity, we omit the dash line from A to C, when A points to both B, C and B points to C.

Theorems & Definitions (4)

• Definition 1
• Definition 2
• Definition 3
• Definition 4