OATAO - Open Archive Toulouse Archive Ouverte Open Access Week

Connecting AI-based Oracles to Blockchains via an Auditable Auction Protocol

Sata, Bernardo and Berlanga, Aizar and Ponzoni Carvalho Chanel, Caroline and Lacan, Jérôme Connecting AI-based Oracles to Blockchains via an Auditable Auction Protocol. (2021) In: 2021 3rd Conference on Blockchain Research & Applications for Innovative Networks and Services (BRAINS), 27 September 2021 - 30 September 2021 (Paris, France).

[img]
Preview
(Document in English)

PDF - Requires a PDF viewer such as GSview, Xpdf or Adobe Acrobat Reader
285kB

Official URL: https://doi.org/10.1109/BRAINS52497.2021.9569808

Abstract

The use of Artificial Intelligence (AI), in particular sequential decision-making (SDM) algorithms, in blockchains can greatly improve their autonomy and general features. In this context, this paper proposes the protocol CONDOR (Connecting ai-based Oracles to blockchaiN via an auDitable auctiOn pRotocol) between a smart contract and some off-chain AI-based oracles to enable the smart contract to choose among AI solution proposals while inciting those oracles to provide non-forged results. The main principle is to consider the AI outcomes as auctions that can be challenged and audited through a dispute phase. An Ethereum implementation of the aforementioned protocol was built in order to assess its scalability and time performances.

Item Type:Conference or Workshop Item (Paper)
Additional Information:Thanks to the IEEE (Institute of Electrical and Electronics Engineers). This paper is available at : https://ieeexplore.ieee.org/document/9569808 “© 2021 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.
Audience (conference):International conference proceedings
Uncontrolled Keywords:
Institution:Université de Toulouse > Institut Supérieur de l'Aéronautique et de l'Espace - ISAE-SUPAERO (FRANCE)
Laboratory name:
Statistics:download
Deposited On:12 Jan 2022 09:37

Repository Staff Only: item control page