# 偵察

標記為「偵察」的 4 篇文章

Identifying LLM Defenses

Map the 防禦層 of an LLM application through systematic probing and error analysis.

分析 LLM application error messages to extract information about system architecture, models, and 防禦層.

Hands-on 技術 for extracting hidden 系統提示詞s from LLM-powered applications using direct asking, role-play, instruction replay, and other methods.

Use various 技術 to 系統性地 extract and reconstruct the full 系統提示詞 of an LLM application, combining direct, indirect, and incremental extraction methods.