IIT Bombay与Adobe新方法可近乎完美还原LLM提示词
Researchers can now reverse-engineer LLM prompts from output text with near-perfect accuracy
IIT Bombay和Adobe搞了个反向模型，能从AI输出还原你藏的提示词，不用看权重就能扒出系统提示，提示词秘密要保不住了。
IIT Bombay和Adobe Research的研究者构建了一个逆语言模型，能从LLM输出文本反向重建原始提示词。
该方法名为Previous-Token Prediction，达到近乎完美的准确率。它不需要访问模型权重，并且能跨不同模型使用。
这一能力对依赖专有系统提示词的公司构成严重安全风险。
Researchers can now reverse-engineer LLM prompts from output text with near-perfect accuracy
Researchers at IIT Bombay and Adobe Research have built an inverse language model that reconstructs the original prompt from an LLM's output with near-perfect accuracy. Their method, called "Previous-Token Prediction," doesn't need access to model weights and works across different models. For companies relying on proprietary system prompts, this could be a serious security risk. The article Researchers can now reverse-engineer LLM prompts from output text with near-perfect accuracy appeared first on The Decoder .
This report is categorized under AITOP's "Papers" desk. Within our cross-regional analytical framework, it directly maps to AI developer toolchains, coding agents, and engineering workflows. Key entities and technical topics under continuous tracking include Previous-Token Prediction, Adobe Research, IIT Bombay, 提示词工程.
Source attribution: curated from Decoder (@Matthias Bastian).