Trugard and Webacy have introduced an AI tool designed to detect crypto wallet address poisoning, boasting a success rate of 97%. The tool, integrated into Webacy's suite of crypto decisioning tools, employs machine learning algorithms trained on live transaction data and onchain analytics. Address poisoning occurs when attackers send small amounts of cryptocurrency from addresses that closely mimic legitimate ones, tricking users into sending funds to the wrong address. This technique exploits user reliance on partial address matching and clipboard history. A report revealed over 270 million address poisoning attempts on BNB Chain and Ethereum from July 2022 to June 2024, with 6,000 successful attempts resulting in losses exceeding $83 million. Trugard's CTO Jeremiah O'Connor emphasized that their tool outperforms traditional detection systems by adapting to evolving attack methods. By continuously training the model with new data and simulated scenarios, the AI can effectively recognize patterns beyond human capabilities, enhancing its robustness against future threats.

Source 🔗