Detection and Analysis of Sensitive and Illegal Content on the Ethereum Blockchain Using Machine Learning Techniques

2025-12-19

AI Summary

Detecting covertly stored sensitive or illicit content—such as personal privacy data, pornographic images, and divisive or discriminatory speech—on the decentralized, immutable Ethereum blockchain poses significant challenges. Method: We propose the first multimodal collaborative detection framework tailored for Ethereum. It features a novel on-chain fragmented-data reconstruction algorithm to structurally restore text, images, and files; integrates FastText-based sentiment analysis, NSFWJS-based image classification, and on-chain semantic parsing. Contribution/Results: We empirically uncover and validate a previously undocumented phenomenon: targeted embedding of sensitive information concerning Chinese public officials. Our framework successfully reconstructed 175 files, 296 images, and 91,206 text segments. Evaluation shows 90% accuracy in sentiment classification and 100% precision (7/7) in identifying non-safe-for-work (NSFW) images. This work establishes a foundational methodology for forensic analysis and content moderation on permissionless blockchains.

Technology Category

• Natural Language Processing: Ethics — Bias, Fairness, Transparency & Privacy
• Data Mining & Knowledge Management: Mining of Visual, Multimedia & Multimodal Data
• Machine Learning: Large Multimodal Models (LMMs)

Application Category

• Web Mining and Content Analysis: Large pretrained models with web data
• Security and Privacy: Blockchains and distributed ledgers
• Economics, Online Markets and Human Computation: Economic aspects of blockchain and cryptocurrencies

Abstract

Blockchain technology, lauded for its transparent and immutable nature, introduces a novel trust model. However, its decentralized structure raises concerns about potential inclusion of malicious or illegal content. This study focuses on Ethereum, presenting a data identification and restoration algorithm. Successfully recovering 175 common files, 296 images, and 91,206 texts, we employed the FastText algorithm for sentiment analysis, achieving a 0.9 accuracy after parameter tuning. Classification revealed 70,189 neutral, 5,208 positive, and 15,810 negative texts, aiding in identifying sensitive or illicit information. Leveraging the NSFWJS library, we detected seven indecent images with 100% accuracy. Our findings expose the coexistence of benign and harmful content on the Ethereum blockchain, including personal data, explicit images, divisive language, and racial discrimination. Notably, sensitive information targeted Chinese government officials. Proposing preventative measures, our study offers valuable insights for public comprehension of blockchain technology and regulatory agency guidance. The algorithms employed present innovative solutions to address blockchain data privacy and security concerns.

Problem

• Detecting sensitive and illegal content on Ethereum blockchain
• Analyzing sentiment and classifying text data using machine learning
• Identifying explicit images and harmful information for regulatory guidance

Innovation

• FastText algorithm for sentiment analysis with high accuracy
• NSFWJS library for indecent image detection with 100% accuracy
• Data identification and restoration algorithm for recovering files and texts