Deakin University
Browse

File(s) not publicly available

Recording Behaviors of Artificial Intelligence in Blockchains

journal contribution
posted on 2023-02-14, 03:05 authored by Y Zhang, J Zhao, J Jiang, Y Zhu, L Wang, Yong XiangYong Xiang
The key challenges of current blockchain, such as low throughput, high latency, and poor scalability, hinder its future development. The recent advances in artificial intelligence (AI) can well overcome these challenges, thus spurring an increasing number of organizations and individuals to equip blockchain with AI, making blockchain become more intelligent. However, AI behaviors need to be supervised for ex post forensics in case of dispute and accountability. This motivates us to envision a model to record the AI behaviors in intelligent blockchain. In this paper, we propose such a model called AI-Tracer, which leverages proxy re-encryption based on Schnorr signature as well as InterPlanetary File System (IPFS) to be integrated into intelligent blockchain. AI-Tracer generates AI-digest during the AI learning process and encrypts it with proxy re-encryption. IPFS is responsible to store the encrypted AI-digest and returns a hash pointer related to AI-digest for further verification. The authorized user can verify the validity of AI-digest by leveraging advanced features of blockchain technology and only the valid AI-digest can be uploaded to intelligent blockchain, which implements trusted tracking for AI behaviors. AI-Tracer achieves fine-grained access control of AI-digest via proxy re-encryption. A user can retrieve the plaintext of AI-digest from intelligent blockchain with the specific authorization. We conduct theoretical analysis to indicate the privacy and security of AI-Tracer. Moreover, we deploy AI-Tracer on the Hyperledger Fabric and demonstrate the efficiency and effectiveness of AI-Tracer through extensive experiments.

History

Journal

IEEE Transactions on Artificial Intelligence

Volume

PP

Pagination

1-12

ISSN

2691-4581

eISSN

2691-4581

Publication classification

C1 Refereed article in a scholarly journal

Issue

99

Publisher

Institute of Electrical and Electronics Engineers (IEEE)

Usage metrics

    Research Publications

    Categories

    No categories selected

    Exports

    RefWorks
    BibTeX
    Ref. manager
    Endnote
    DataCite
    NLM
    DC