# defense-bypass
標記為「defense-bypass」的 14 篇文章
Lab: Defense Bypass Basics
Learn basic techniques to bypass simple LLM defenses including keyword filters, instruction reinforcement, and output validators using encoding, reformulation, and indirect approaches.
CTF: Defense Breaker
Bypass progressively sophisticated defense mechanisms protecting an AI system. Each level introduces a new defense layer while retaining all previous defenses, testing your ability to adapt and chain bypass techniques.
Building Defense Bypass Chains
Combine multiple bypass techniques into reliable chains that defeat layered defenses.
Lab: Systematic Defense Bypass
Hands-on lab for methodically identifying, categorizing, and bypassing common LLM defense mechanisms including input filters, output filters, and system prompt hardening.
Multimodal Defense Bypass Techniques
Techniques for bypassing safety filters that only analyze individual modalities.
Defense Bypass Quick Reference
Quick reference card for common AI defense mechanisms and their known bypass techniques, organized by defense type.
實驗室: 防禦 Bypass Basics
Learn basic techniques to bypass simple LLM defenses including keyword filters, instruction reinforcement, and output validators using encoding, reformulation, and indirect approaches.
CTF：Defense Breaker
繞過逐步增強、保護 AI 系統的防禦機制。每一關加入新的防禦層同時保留所有先前防禦，考驗你適應與串接繞過技術的能力。
CTF：防禦挑戰賽
競賽式 CTF 挑戰，要求你繞過多層 AI 安全防禦以擷取旗幟——測試你的防禦規避技能。
中階 AI 紅隊實驗室
構成專業 AI 紅隊演練骨幹的核心攻擊技術實驗室——防禦繞過、代理利用、RAG 投毒與更多。
Building 防禦 Bypass Chains
Combine multiple bypass techniques into reliable chains that defeat layered defenses.
實驗室: Systematic 防禦 Bypass
Hands-on lab for methodically identifying, categorizing, and bypassing common LLM defense mechanisms including input filters, output filters, and system prompt hardening.
Multimodal 防禦 Bypass Techniques
Techniques for bypassing safety filters that only analyze individual modalities.
防禦繞過快速參考
常見 AI 防禦機制及其已知繞過技術的快速參考卡，依防禦類型組織。