研究人员实现从LLM输出文本近乎完美地逆向工程提示词
原标题：Researchers can now reverse-engineer LLM prompts from output text with near-perfect accuracy
AI 摘要
IIT Bombay和Adobe Research的研究人员开发了一种名为“Previous-Token Prediction”(PTP)的方法，能够仅根据LLM的输出文本以近乎完美的准确率重建原始提示词，无需访问模型权重，甚至适用于第三方模型。该方法通过训练一个逆语言模型来预测前一个token，并能在不知道具体模型的情况下提取提示词，这可能导致专有系统提示词和用户敏感查询的泄露，构成广泛的安全问题。
正文节选
Researchers can now reverse-engineer LLM prompts from output text with near-perfect accuracy Researchers at IIT Bombay and Adobe Research have developed a method that can reconstruct prompts fed to large language models with near-perfect accuracy, using only the text output. The approach works without access to model weights and even applies to third-party models. Large language models generate text by predicting the next most likely word, token by token. Reversing that process and reconstructin