# prompt-hardening
標記為「prompt-hardening」的 4 篇文章
Patterns for Hardening System Prompts
Practical patterns and techniques for hardening LLM system prompts against injection, extraction, and manipulation attacks, including structural defenses, instruction hierarchy, delimiter strategies, and defense-in-depth approaches.
prompt-hardeningsystem-promptdefense-patternsprompt-injectioninstruction-hierarchy
Secure Development
Security-by-design principles for AI applications including defensive prompt engineering, input validation, output sanitization, and integrating security testing into CI/CD pipelines.
defensesecure-developmentprompt-hardeninginput-validationCI/CD
Patterns for Hardening System Prompts
Practical patterns and techniques for hardening LLM system prompts against injection, extraction, and manipulation attacks, including structural defenses, instruction hierarchy, delimiter strategies, and defense-in-depth approaches.
prompt-hardeningsystem-promptdefense-patternsprompt-injectioninstruction-hierarchy
安全開發
AI 應用程式的安全設計原則，包含防禦性提示詞工程、輸入驗證、輸出清理，以及將安全測試整合至 CI/CD 管線。
defensesecure-developmentprompt-hardeninginput-validationCI/CD