Visible to the public Blockchain Based Audit Trailing of XAI Decisions: Storing on IPFS and Ethereum Blockchain

TitleBlockchain Based Audit Trailing of XAI Decisions: Storing on IPFS and Ethereum Blockchain
Publication TypeConference Paper
Year of Publication2021
AuthorsMalhotra, Diksha, Srivastava, Shubham, Saini, Poonam, Singh, Awadhesh Kumar
Conference Name2021 International Conference on COMmunication Systems NETworkS (COMSNETS)
Date PublishedJan. 2021
PublisherIEEE
ISBN Number978-1-7281-9127-0
Keywordsartificial intelligence, blockchain, cryptography, Databases, File systems, pubcrawl, Regulators, resilience, Resiliency, Scalability, smart contracts, xai
AbstractExplainable Artificial Intelligence (XAI) generates explanations which are used by regulators to audit the responsibility in case of any catastrophic failure. These explanations are currently stored in centralized systems. However, due to lack of security and traceability in centralized systems, the respective owner may temper the explanations for his convenience in order to avoid any penalty. Nowadays, Blockchain has emerged as one of the promising technologies that might overcome the security limitations. Hence, in this paper, we propose a novel Blockchain based framework for proof-of-authenticity pertaining to XAI decisions. The framework stores the explanations in InterPlanetary File System (IPFS) due to storage limitations of Ethereum Blockchain. Further, a Smart Contract is designed and deployed in order to supervise the storage and retrieval of explanations from Ethereum Blockchain. Furthermore, to induce cryptographic security in the network, an explanation's hash is calculated and stored in Blockchain too. Lastly, we perform the cost and security analysis of our proposed system.
URLhttps://ieeexplore.ieee.org/document/9352908
DOI10.1109/COMSNETS51098.2021.9352908
Citation Keymalhotra_blockchain_2021