Trust in the gig economy lives and dies by reputation. Platforms like Upwork and Fiverr use review scores as stand-ins for credibility, yet the systems underlying those scores are opaque, siloed, and surprisingly easy to manipulate. This paper presents VeriTrust, a fully working AI-powered reputation system that pairs blockchain immutability with natural language processing to give freelancers a tamper-proof, portable reputation they genuinely own. At its core, VeriTrust runs an application-level Proof-of-Work blockchain with SHA-256 mining and RSA-2048 cryptographic signing so that every review is verifiably authentic. Two Solidity smart contracts are deployed on Polygon Amoy—one storing full data for maximum auditability, and a leaner VeriTrustLite variant that trims gas costs by roughly 80% through struct packing, custom errors, and hash-only storage. A three-step prepare/confirm write protocol ties each on-chain anchor to the matching PostgreSQL record, and reputation is keyed on RSA public keys rather than wallet addresses, so users can carry their history across chains and platforms without asking anyone’s permission. A React.js DApp with MetaMask integration, a live blockchain explorer, and a chain indexer round out the implementation. Smart contract test coverage is 100% across all statement branches.
Blockchain, Decentralized Application, Gig Economy, Natural Language Processing, Proof-Of-Work, Reputation Systems, RSA Cryptography, Sentiment Analysis, Smart Contracts.
IRE Journals:
Muiz Zatam, Angad Muthyala, Sarvesh Varvatkar, Jaspreet Kaur "VeriTrust: An AI-Powered Decentralized Reputation System for the Gig Economy" Iconic Research And Engineering Journals Volume 9 Issue 10 2026 Page 1687-1691 https://doi.org/10.64388/IREV9I10-1716368
IEEE:
Muiz Zatam, Angad Muthyala, Sarvesh Varvatkar, Jaspreet Kaur
"VeriTrust: An AI-Powered Decentralized Reputation System for the Gig Economy" Iconic Research And Engineering Journals, 9(10) https://doi.org/10.64388/IREV9I10-1716368