Researchers have developed a machine learning model to predict fraudulent 'memecoins' on the Solana blockchain. These coins are designed to quickly gain value and then disappear, taking investors' funds with them. The team used data from over 6 million tokens to train their model, which can detect potential rug pulls within just five minutes of trading. This study aims to help protect investors by identifying early warning signs of these scams. --- Why it matters: This research matters because it provides a practical framework for detecting and preventing DeFi fraud on high-throughput chains like Solana. By developing an effective early detection system, investors can be warned before they invest in potentially fraudulent coins. Source: https://arxiv.org/abs/2608.20271