Researchers can now reverse-engineer LLM prompts from output text with near-perfect accuracy

Researchers at IIT Bombay and Adobe Research have developed an inverse language model called 'Previous-Token Prediction' that reconstructs the original prompt from an LLM's output with near-perfect accuracy, without needing access to model weights and working across different models. This poses a serious security risk for companies relying on proprietary system prompts.

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 https://the-decoder.com/researchers-can-now-reverse-engineer-llm-prompts-from-output-text-with-near-perfect-accuracy/ appeared first on The Decoder https://the-decoder.com .