mlsanityData to 7 Oct 2026

SoK: Blockchain-Based Decentralized AI (DeAI)

arXiv 2411.17461 ↗First posted 26 Nov 2024cs.LG cs.AI cs.CRcited by 6

Not on the map. Why?

Abstract (arXiv)

Centralization enhances the efficiency of Artificial Intelligence (AI) but also introduces critical challenges, including single points of failure, inherent biases, data privacy risks, and scalability limitations. To address these issues, blockchain-based Decentralized Artificial Intelligence (DeAI) has emerged as a promising paradigm that leverages decentralization and transparency to improve the trustworthiness of AI systems. Despite rapid adoption in industry, the academic community lacks a systematic analysis of DeAI's technical foundations, opportunities, and challenges. This work presents the first Systematization of Knowledge (SoK) on DeAI, offering a formal definition, a taxonomy of existing solutions based on the AI lifecycle, and an in-depth investigation of the roles of blockchain in enabling secure and incentive-compatible collaboration. We further review security risks across the DeAI lifecycle and empirically evaluate representative mitigation techniques. Finally, we highlight open research challenges and future directions for advancing blockchain-based DeAI.

Key facts. Cited by 6 papers in the map (data through 7 Oct 2026). Builds on 85 of its 226 references that are in the map. First posted on arXiv 26 Nov 2024.

Builds on

85 of 226 references.

References · 85

  1. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
  2. 2020Language Models are Few-Shot Learnerscited by 32,199
  3. 2015Distilling the Knowledge in a Neural Networkcited by 10,076
  4. 2016Communication-Efficient Learning of Deep Networks from Decentralized Datacited by 7,592
  5. 2017mixup: Beyond Empirical Risk Minimizationcited by 5,155
  6. 2019Advances and Open Problems in Federated Learningcited by 3,021
  7. 2022Constitutional AI: Harmlessness from AI Feedbackcited by 2,950
  8. 2016Deep Learning with Differential Privacycited by 2,682
  9. 2020Extracting Training Data from Large Language Modelscited by 2,144
  10. 2018Datasheets for Datasetscited by 1,371
  11. 2018How To Backdoor Federated Learningcited by 745
  12. 2023A Watermark for Large Language Modelscited by 667
38 more
  1. 2016Stealing Machine Learning Models via Prediction APIscited by 602
  2. 2019Eternal Sunshine of the Spotless Net: Selective Forgetting in Deep Networkscited by 599
  3. 2017Can Decentralized Algorithms Outperform Centralized Algorithms? A Case Study for Decentralized Parallel Stochastic Gradient Descentcited by 496
  4. 2019Local Model Poisoning Attacks to Byzantine-Robust Federated Learningcited by 479
  5. 2018Spectral Signatures in Backdoor Attackscited by 457
  6. 2017Efficient Processing of Deep Neural Networks: A Tutorial and Surveycited by 427
  7. 2019Federated Machine Learning: Concept and Applicationscited by 409
  8. 2023A Survey on Large Language Model (LLM) Security and Privacy: The Good, the Bad, and the Uglycited by 380
  9. 2021Federated Learning on Non-IID Data: A Surveycited by 345
  10. 2020SplitFed: When Federated Learning Meets Split Learningcited by 308
  11. 2020Attack of the Tails: Yes, You Really Can Backdoor Federated Learningcited by 307
  12. 2020QPLEX: Duplex Dueling Multi-Agent Q-Learningcited by 267
  13. 2019Asynchronous Federated Optimizationcited by 264
  14. 2017Embedding Watermarks into Deep Neural Networkscited by 227
  15. 2019A Survey on Distributed Machine Learningcited by 187
  16. 2024Security and Privacy Challenges of Large Language Models: A Surveycited by 179
  17. 2021On the Necessity of Auditable Algorithmic Definitions for Machine Unlearningcited by 164
  18. 2018The Malicious Use of Artificial Intelligence: Forecasting, Prevention, and Mitigationcited by 159
  19. 2018PRADA: Protecting against DNN Model Stealing Attackscited by 159
  20. 2022Decentralized Federated Learning: Fundamentals, State of the Art, Frameworks, Trends, and Challengescited by 137
  21. 2020Byzantine-Robust Learning on Heterogeneous Datasets via Bucketingcited by 125
  22. 2019Local SGD with Periodic Averaging: Tighter Analysis and Adaptive Synchronizationcited by 106
  23. 2023Decentralized Federated Learning: A Survey and Perspectivecited by 86
  24. 2021Proof-of-Learning: Definitions and Practicecited by 81
  25. 2023Fixing by Mixing: A Recipe for Optimal Byzantine ML under Heterogeneitycited by 64
  26. 2023CodeLMSec Benchmark: Systematically Evaluating and Finding Security Vulnerabilities in Black-Box Code Language Modelscited by 52
  27. 2024zkLLM: Zero Knowledge Proofs for Large Language Modelscited by 51
  28. 2024Consent in Crisis: The Rapid Decline of the AI Data Commonscited by 45
  29. 2019Asynchronous Decentralized SGD with Quantized and Local Updatescited by 35
  30. 2024Revisiting Adversarial Training at Scalecited by 33
  31. 2023A Survey on Decentralized Federated Learningcited by 27
  32. 2023Robust Distributed Learning: Tight Error Bounds and Breakdown Point under Data Heterogeneitycited by 25
  33. 2021SoK: Decentralized Finance (DeFi)cited by 23
  34. 2022Trusted AI in Multi-agent Systems: An Overview of Privacy and Security for Distributed Learningcited by 22
  35. 2023Tools for Verifying Neural Models' Training Datacited by 21
  36. 2024opML: Optimistic Machine Learning on Blockchaincited by 20
  37. 2024Shake to Leak: Fine-tuning Diffusion Models Can Amplify the Generative Privacy Riskcited by 17
  38. 2020BitTensor: A Peer-to-Peer Intelligence Marketcited by 15

50 most cited of 85 All 85 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 1; 2025: 1; 2026: 4.

6 papers.