Discovering NFT Rug Pulls: Matching Behavior PatternsUsing Graph Isomorphism Networks

【Author】 Sharma, Trishie; Shukla, Sandeep Kumar

【Source】ACM TRANSACTIONS ON INTERNET TECHNOLOGY

【影响因子】3.989

【Abstract】Amid the surge of Non-Fungible Tokens (NFTs) in blockchain, this study introduces a meticulous method-ology focusing on transaction behaviors to unveil rug pulls - a critical issue impacting financial securityand trust in the NFT landscape. Using a Graph Isomorphism Network (GIN) model with 6 behavioral pat-terns obtained from transaction sequences, we create a "Rug Pull Pattern Matcher" model. We provide acomprehensive analysis by applying the model on two datasets - creator's transactions from 50 reputableNFT projects and 32 reported rug pulls. Our work utilizes automated labeling to categorize addresses and ouranalysis reveals several interconnected NFT creator activities. We present an in-depth mapping of fund flowsand creator interactions exposing suspicious behaviors like artificial inflation and intricate network collab-orations among creators. The results of our proposed model demonstrate the efficacy of our methodologywith 75.4% accuracy and 85.9% precision on the dataset of reported rug pulls. This work provides compara-tive analyses of genuine and malicious creator networks to elucidate their structural differences, helping toidentify genuine and potentially fraudulent NFT activities.

【Keywords】Blockchain; cryptocurrency frauds; ethereum; graph theory; illicit activi-ties; non-fungible tokens; rug pull

【发表时间】2025 AUG

【收录时间】2025-09-27

【文献类型】

【主题类别】

--