• Chamodi Liyanage
• Shan Wanigasuriya
• Malshan Rathnayaka
• Jehan Silva

The digital revolution has resulted in a surge of intellectual property (IP) across textual, visual, and multimedia formats, exposing content creators to increasing risks of plagiarism and unauthorized usage. Centralized IP protection systems are often slow, jurisdiction-bound, and incapable of detecting semantically or visually similar content that has been paraphrased, translated, or remixed. This research proposes a decentralized IP protection platform that integrates AI- powered semantic and multimedia similarity detection with blockchain-based ownership verification and metadata storage. Our methodology includes transformer-based vision-language models for video analysis, Sentence-BERT and FAISS indexing for semantic similarity checking, and federated learning for privacy-preserving, real-time model adaptability. Experimental results demonstrate the system’s ability to detect IP infringement across modalities with high precision, while leveraging Ethereum smart contracts and IPFS for secure, transparent content registration. The platform not only improves the speed and accuracy of IP registration but also ensures verifiable authorship and supports dynamic content adaptation in decentralized environments. This research contributes a modular, multimodal, and scalable solution for modern IP governance.

Intellectual property protection, semantic similarity detection, video similarity checking, decentralized storage, blockchain, federated learning, IPFS, smart contracts, transformer models

"Decentralized Intellectual Property (IP) Protection Platform with AI-Powered Similarity Detection", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.12, Issue 11, page no.d86-d92, November-2025, Available :http://www.jetir.org/papers/JETIR2511311.pdf

"Decentralized Intellectual Property (IP) Protection Platform with AI-Powered Similarity Detection", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.12, Issue 11, page no. ppd86-d92, November-2025, Available at : http://www.jetir.org/papers/JETIR2511311.pdf