一句话：提出 OctopusGuard，用 K 线数据增强多模态 LLM，检测 DeFi 中行为驱动的代币诈骗。
DeFi 中的代币诈骗正从简单的合约漏洞利用转向行为驱动的欺诈，涉及混淆代码、异常资金流与欺骗性市场活动。现有基于大语言模型的漏洞检测方法仍依赖预定义模式，缺乏深层语义推理，难以发现新型诈骗。为此，本文提出 OctopusGuard：一种由多模态大语言模型驱动的 K 线增强代币诈骗检测器。其核心思路是引入 K 线（市场行情）信号，使多模态 LLM 能结合代码/行为与市场活动进行语义推理，从而识别新型代币诈骗。摘要未报告具体实现细节、数据集与评估结果；从标题与摘要看，评估应围绕代币诈骗检测任务展开，但原文未给出指标。
Token scams in Decentralized Finance (DeFi) have become more sophisticated, shifting from simple contract exploits to behavior-driven fraud involving obfuscated code, abnormal fund flows, and deceptive market activity. While recent works leverage large language models (LLMs) for vulnerability detection, existing methods still depend on predefined patterns and lack deep semantic reasoning, limiting their ability to detect novel scams.