Blockchain-oriented approach for detecting cyber-attack transactions

Abstract With the high-speed development of decentralized applications, account-based blockchain platforms have become a hotbed various financial scams and hacks due to their anonymity high value. Financial security has top priority with sustainable blockchain-based because an increasing number cyber attacks, which resulted in huge loss crypto assets recent years. Therefore, it is imperative study real-time detection attacks facilitate effective supervision regulation. To this end, paper proposes weighted extended isolation forest algorithms designs novel framework for cyber-attack transactions by thoroughly studying summarizing real-world examples. Furthermore, develops new approach locating compromised address attack resolve data scarcity hack addresses reduce time consumption. Moreover, three experiments are carried out not only apply on different types but also compare proposed widely used existing methods. The results demonstrate efficiency generality approach. Finally, lower consumption robustness our method were validated through additional experiments. In conclusion, blockchain-oriented can handle significant scope applications.