# multi-layer
標記為「multi-layer」的 4 篇文章
分層防禦策略
為 AI 應用實施縱深防禦：設計獨立的防禦層、確保正交涵蓋，並管理多層安全的複雜度。
defense-in-depthlayered-defensesecurity-architecturemulti-layerstrategy
Lab: Defense Engineering Lab
Expert-level lab for building and evaluating a production-grade multi-layer AI defense system including input classifiers, output monitors, semantic analysis, and 對抗性 robustness testing.
labexpertdefense-engineeringproductionmulti-layer
Lab: Full-Stack AI Exploitation
串聯 vulnerabilities across UI, API, model, and infrastructure layers to achieve full-stack compromise of an AI application. 學習 to identify cross-layer attack paths and build exploit chains that no single-layer defense can prevent.
labexpertfull-stackexploit-chainmulti-layerhands-on
Multi-Layer Input Validation
Step-by-step walkthrough for building a defense-in-depth input validation pipeline that combines regex matching, semantic similarity, ML classification, and rate limiting into a unified validation system for LLM applications.
defense-in-depthinput-validationpipelinemulti-layerdefensewalkthrough