# json
標記為「json」的 7 篇文章
JSON Output 利用 Basics
利用 LLM JSON mode to bypass content filters與extract information through structured output channels.
Lab: Structured Output Manipulation
探索 how JSON mode, schema injection, and forced output formats can bypass LLM safety filters and manipulate structured responses.
JSON 注入 Basics
注入adversarial content through JSON-formatted inputs to exploit structured data processing.
實驗室: JSON Input 注入
動手lab exploring how adversarial payloads injected through structured JSON inputs can manipulate language model behavior,bypass schema validation,exploit parsing inconsistencies.
透過結構化資料格式的注入
透過 JSON、XML、YAML 與 SQL 等結構化資料格式注入提示詞。
JSON Injection 攻擊 詳解
Exploit JSON parsing and generation in LLM applications to inject payloads through structured data boundaries.
XML and JSON Injection in LLM Apps
Walkthrough of exploiting XML and JSON parsing in LLM applications for injection and data manipulation.