Researchers have developed a new framework for analyzing blockchain activity to identify persistent behavioral patterns, which can aid in forensic investigations. This system constructs "behavior sentences" from transactions and uses embeddings to capture individual actions and user behavior over time. Evaluations on Ethereum data demonstrated the framework's ability to uncover both routine activities like DEX trading and NFT usage, as well as malicious behaviors such as phishing, bot operations, and rug-pull schemes. The patterns identified remained stable across different observation periods, allowing for the detection of long-term behaviors. AI
IMPACT This framework could enhance the detection of illicit activities and improve attribution in blockchain forensics.
RANK_REASON The cluster contains a research paper detailing a new framework for blockchain analysis. [lever_c_demoted from research: ic=1 ai=0.4]
AI-generated summary · Google Gemini · from 1 sources. How we write summaries →
