# 大模型安全权威指南 | AI Security Guide

## Docs

- [大模型安全权威指南](https://yeasy.gitbook.io/ai_security_guide/readme.md)
- [第一章 大语言模型安全导论](https://yeasy.gitbook.io/ai_security_guide/di-yi-bu-fen-ji-chu-pian/01_intro.md)
- [1.1 大语言模型概述](https://yeasy.gitbook.io/ai_security_guide/di-yi-bu-fen-ji-chu-pian/01_intro/1.1_llm_overview.md)
- [1.2 为什么大语言模型安全至关重要](https://yeasy.gitbook.io/ai_security_guide/di-yi-bu-fen-ji-chu-pian/01_intro/1.2_why_security_matters.md)
- [1.3 大语言模型安全与传统安全的异同](https://yeasy.gitbook.io/ai_security_guide/di-yi-bu-fen-ji-chu-pian/01_intro/1.3_llm_vs_traditional.md)
- [1.4 大语言模型安全威胁全景图](https://yeasy.gitbook.io/ai_security_guide/di-yi-bu-fen-ji-chu-pian/01_intro/1.4_threat_landscape.md)
- [本章小结](https://yeasy.gitbook.io/ai_security_guide/di-yi-bu-fen-ji-chu-pian/01_intro/summary.md)
- [第二章 大语言模型安全基础](https://yeasy.gitbook.io/ai_security_guide/di-yi-bu-fen-ji-chu-pian/02_fundamentals.md)
- [2.1 大语言模型架构与安全边界](https://yeasy.gitbook.io/ai_security_guide/di-yi-bu-fen-ji-chu-pian/02_fundamentals/2.1_architecture_boundary.md)
- [2.2 训练过程中的安全考量](https://yeasy.gitbook.io/ai_security_guide/di-yi-bu-fen-ji-chu-pian/02_fundamentals/2.2_training_security.md)
- [2.3 推理阶段的安全挑战](https://yeasy.gitbook.io/ai_security_guide/di-yi-bu-fen-ji-chu-pian/02_fundamentals/2.3_inference_security.md)
- [2.4 安全对齐技术入门](https://yeasy.gitbook.io/ai_security_guide/di-yi-bu-fen-ji-chu-pian/02_fundamentals/2.4_alignment_intro.md)
- [2.5 推理模型安全深度分析](https://yeasy.gitbook.io/ai_security_guide/di-yi-bu-fen-ji-chu-pian/02_fundamentals/2.5_reasoning_model_security.md)
- [本章小结](https://yeasy.gitbook.io/ai_security_guide/di-yi-bu-fen-ji-chu-pian/02_fundamentals/summary.md)
- [第三章 安全框架与标准](https://yeasy.gitbook.io/ai_security_guide/di-yi-bu-fen-ji-chu-pian/03_frameworks.md)
- [3.1 OWASP 大语言模型十大风险解析](https://yeasy.gitbook.io/ai_security_guide/di-yi-bu-fen-ji-chu-pian/03_frameworks/3.1_owasp_top10.md)
- [3.2 NIST AI 风险管理框架](https://yeasy.gitbook.io/ai_security_guide/di-yi-bu-fen-ji-chu-pian/03_frameworks/3.2_nist_framework.md)
- [3.3 行业安全标准与最佳实践](https://yeasy.gitbook.io/ai_security_guide/di-yi-bu-fen-ji-chu-pian/03_frameworks/3.3_industry_standards.md)
- [3.4 MITRE ATLAS 对抗矩阵](https://yeasy.gitbook.io/ai_security_guide/di-yi-bu-fen-ji-chu-pian/03_frameworks/3.4_mitre_atlas.md)
- [本章小结](https://yeasy.gitbook.io/ai_security_guide/di-yi-bu-fen-ji-chu-pian/03_frameworks/summary.md)
- [第四章 提示注入攻击与防御](https://yeasy.gitbook.io/ai_security_guide/di-er-bu-fen-gong-ji-pian/04_prompt_injection.md)
- [4.1 提示注入原理与分类](https://yeasy.gitbook.io/ai_security_guide/di-er-bu-fen-gong-ji-pian/04_prompt_injection/4.1_principles.md)
- [4.2 直接提示注入技术](https://yeasy.gitbook.io/ai_security_guide/di-er-bu-fen-gong-ji-pian/04_prompt_injection/4.2_direct_injection.md)
- [4.3 间接提示注入技术](https://yeasy.gitbook.io/ai_security_guide/di-er-bu-fen-gong-ji-pian/04_prompt_injection/4.3_indirect_injection.md)
- [4.4 公开案例与研究演示分析](https://yeasy.gitbook.io/ai_security_guide/di-er-bu-fen-gong-ji-pian/04_prompt_injection/4.4_case_studies.md)
- [4.5 分层防御与安全门控](https://yeasy.gitbook.io/ai_security_guide/di-er-bu-fen-gong-ji-pian/04_prompt_injection/4.5_injection_defense.md)
- [4.6 长上下文的安全风险](https://yeasy.gitbook.io/ai_security_guide/di-er-bu-fen-gong-ji-pian/04_prompt_injection/4.6_long_context_risks.md)
- [本章小结](https://yeasy.gitbook.io/ai_security_guide/di-er-bu-fen-gong-ji-pian/04_prompt_injection/summary.md)
- [第五章 越狱攻击](https://yeasy.gitbook.io/ai_security_guide/di-er-bu-fen-gong-ji-pian/05_jailbreak.md)
- [5.1 越狱攻击概述](https://yeasy.gitbook.io/ai_security_guide/di-er-bu-fen-gong-ji-pian/05_jailbreak/5.1_jailbreak_overview.md)
- [5.2 经典越狱技术剖析](https://yeasy.gitbook.io/ai_security_guide/di-er-bu-fen-gong-ji-pian/05_jailbreak/5.2_classic_techniques.md)
- [5.3 多模态越狱攻击](https://yeasy.gitbook.io/ai_security_guide/di-er-bu-fen-gong-ji-pian/05_jailbreak/5.3_multimodal_attacks.md)
- [5.4 越狱检测与防御实践](https://yeasy.gitbook.io/ai_security_guide/di-er-bu-fen-gong-ji-pian/05_jailbreak/5.4_jailbreak_defense.md)
- [5.5 多模态安全防御体系](https://yeasy.gitbook.io/ai_security_guide/di-er-bu-fen-gong-ji-pian/05_jailbreak/5.5_multimodal_defense.md)
- [5.6 自动化越狱方法](https://yeasy.gitbook.io/ai_security_guide/di-er-bu-fen-gong-ji-pian/05_jailbreak/5.6_automated_jailbreak_methods.md)
- [本章小结](https://yeasy.gitbook.io/ai_security_guide/di-er-bu-fen-gong-ji-pian/05_jailbreak/summary.md)
- [第六章 数据与模型攻击](https://yeasy.gitbook.io/ai_security_guide/di-er-bu-fen-gong-ji-pian/06_data_model_attacks.md)
- [6.1 训练数据投毒](https://yeasy.gitbook.io/ai_security_guide/di-er-bu-fen-gong-ji-pian/06_data_model_attacks/6.1_data_poisoning.md)
- [6.2 后门攻击](https://yeasy.gitbook.io/ai_security_guide/di-er-bu-fen-gong-ji-pian/06_data_model_attacks/6.2_backdoor_attacks.md)
- [6.3 模型窃取与逆向工程](https://yeasy.gitbook.io/ai_security_guide/di-er-bu-fen-gong-ji-pian/06_data_model_attacks/6.3_model_extraction.md)
- [6.4 成员推理与隐私攻击](https://yeasy.gitbook.io/ai_security_guide/di-er-bu-fen-gong-ji-pian/06_data_model_attacks/6.4_privacy_attacks.md)
- [6.5 离散对抗攻击与模型鲁棒性](https://yeasy.gitbook.io/ai_security_guide/di-er-bu-fen-gong-ji-pian/06_data_model_attacks/6.5_adversarial_robustness.md)
- [6.6 微调与 PEFT 的安全风险](https://yeasy.gitbook.io/ai_security_guide/di-er-bu-fen-gong-ji-pian/06_data_model_attacks/6.6_finetuning_peft_security.md)
- [6.7 恶意模型工件与反序列化攻击](https://yeasy.gitbook.io/ai_security_guide/di-er-bu-fen-gong-ji-pian/06_data_model_attacks/6.7_malicious_model_artifacts.md)
- [本章小结](https://yeasy.gitbook.io/ai_security_guide/di-er-bu-fen-gong-ji-pian/06_data_model_attacks/summary.md)
- [第七章 RAG 与知识库安全](https://yeasy.gitbook.io/ai_security_guide/di-er-bu-fen-gong-ji-pian/07_rag_security.md)
- [7.1 RAG 架构与攻击面](https://yeasy.gitbook.io/ai_security_guide/di-er-bu-fen-gong-ji-pian/07_rag_security/7.1_rag_architecture.md)
- [7.2 知识库投毒攻击](https://yeasy.gitbook.io/ai_security_guide/di-er-bu-fen-gong-ji-pian/07_rag_security/7.2_knowledge_base_poisoning.md)
- [7.3 检索结果操纵](https://yeasy.gitbook.io/ai_security_guide/di-er-bu-fen-gong-ji-pian/07_rag_security/7.3_retrieval_manipulation.md)
- [7.4 文档摄取管线安全](https://yeasy.gitbook.io/ai_security_guide/di-er-bu-fen-gong-ji-pian/07_rag_security/7.4_ingestion_pipeline.md)
- [7.5 向量数据库与嵌入安全](https://yeasy.gitbook.io/ai_security_guide/di-er-bu-fen-gong-ji-pian/07_rag_security/7.5_vector_database_security.md)
- [7.6 检索时的访问控制](https://yeasy.gitbook.io/ai_security_guide/di-er-bu-fen-gong-ji-pian/07_rag_security/7.6_retrieval_access_control.md)
- [7.7 上下文窗口攻击](https://yeasy.gitbook.io/ai_security_guide/di-er-bu-fen-gong-ji-pian/07_rag_security/7.7_context_window_attacks.md)
- [7.8 评测与最佳实践](https://yeasy.gitbook.io/ai_security_guide/di-er-bu-fen-gong-ji-pian/07_rag_security/7.8_rag_evaluation_best_practices.md)
- [本章小结](https://yeasy.gitbook.io/ai_security_guide/di-er-bu-fen-gong-ji-pian/07_rag_security/summary.md)
- [第八章 安全架构设计](https://yeasy.gitbook.io/ai_security_guide/di-san-bu-fen-fang-yu-pian/08_architecture.md)
- [8.1 纵深防御原则](https://yeasy.gitbook.io/ai_security_guide/di-san-bu-fen-fang-yu-pian/08_architecture/8.1_defense_depth.md)
- [8.2 大语言模型安全架构模式](https://yeasy.gitbook.io/ai_security_guide/di-san-bu-fen-fang-yu-pian/08_architecture/8.2_architecture_patterns.md)
- [8.3 权限与访问控制](https://yeasy.gitbook.io/ai_security_guide/di-san-bu-fen-fang-yu-pian/08_architecture/8.3_access_control.md)
- [8.4 安全开发生命周期](https://yeasy.gitbook.io/ai_security_guide/di-san-bu-fen-fang-yu-pian/08_architecture/8.4_security_sdlc.md)
- [8.5 隐私增强技术与数据保护](https://yeasy.gitbook.io/ai_security_guide/di-san-bu-fen-fang-yu-pian/08_architecture/8.5_privacy_enhancing.md)
- [8.6 供应链与基础设施安全](https://yeasy.gitbook.io/ai_security_guide/di-san-bu-fen-fang-yu-pian/08_architecture/8.6_supply_chain.md)
- [本章小结](https://yeasy.gitbook.io/ai_security_guide/di-san-bu-fen-fang-yu-pian/08_architecture/summary.md)
- [第九章 输入输出安全防护](https://yeasy.gitbook.io/ai_security_guide/di-san-bu-fen-fang-yu-pian/09_io_protection.md)
- [9.1 输入验证与过滤](https://yeasy.gitbook.io/ai_security_guide/di-san-bu-fen-fang-yu-pian/09_io_protection/9.1_input_validation.md)
- [9.2 输出内容安全审核](https://yeasy.gitbook.io/ai_security_guide/di-san-bu-fen-fang-yu-pian/09_io_protection/9.2_output_moderation.md)
- [9.3 敏感信息保护](https://yeasy.gitbook.io/ai_security_guide/di-san-bu-fen-fang-yu-pian/09_io_protection/9.3_sensitive_data.md)
- [9.4 AI 生成内容鉴伪与水印技术](https://yeasy.gitbook.io/ai_security_guide/di-san-bu-fen-fang-yu-pian/09_io_protection/9.4_watermarking_detection.md)
- [9.5 下一代 Constitutional Classifiers](https://yeasy.gitbook.io/ai_security_guide/di-san-bu-fen-fang-yu-pian/09_io_protection/9.5_constitutional_classifiers.md)
- [本章小结](https://yeasy.gitbook.io/ai_security_guide/di-san-bu-fen-fang-yu-pian/09_io_protection/summary.md)
- [第十章 安全运营与监控](https://yeasy.gitbook.io/ai_security_guide/di-san-bu-fen-fang-yu-pian/10_operations.md)
- [10.1 安全监控体系](https://yeasy.gitbook.io/ai_security_guide/di-san-bu-fen-fang-yu-pian/10_operations/10.1_monitoring.md)
- [10.2 异常检测与告警](https://yeasy.gitbook.io/ai_security_guide/di-san-bu-fen-fang-yu-pian/10_operations/10.2_anomaly_detection.md)
- [10.3 运行时安全与事件响应](https://yeasy.gitbook.io/ai_security_guide/di-san-bu-fen-fang-yu-pian/10_operations/10.3_incident_response.md)
- [10.4 红队演练与自动化评估](https://yeasy.gitbook.io/ai_security_guide/di-san-bu-fen-fang-yu-pian/10_operations/10.4_red_teaming.md)
- [10.5 服务降级与回退策略](https://yeasy.gitbook.io/ai_security_guide/di-san-bu-fen-fang-yu-pian/10_operations/10.5_fallback_strategy.md)
- [10.6 现代红队工具链](https://yeasy.gitbook.io/ai_security_guide/di-san-bu-fen-fang-yu-pian/10_operations/10.6_modern_redteam_tools.md)
- [本章小结](https://yeasy.gitbook.io/ai_security_guide/di-san-bu-fen-fang-yu-pian/10_operations/summary.md)
- [第十一章 智能体安全基础](https://yeasy.gitbook.io/ai_security_guide/di-si-bu-fen-zhi-neng-ti-an-quan-pian/11_agent_foundations.md)
- [11.1 智能体的实现结构与调用过程](https://yeasy.gitbook.io/ai_security_guide/di-si-bu-fen-zhi-neng-ti-an-quan-pian/11_agent_foundations/11.1_agent_implementation.md)
- [11.2 威胁模型：不可信来源与攻击目标](https://yeasy.gitbook.io/ai_security_guide/di-si-bu-fen-zhi-neng-ti-an-quan-pian/11_agent_foundations/11.2_threat_model.md)
- [11.3 不可靠执行者模型](https://yeasy.gitbook.io/ai_security_guide/di-si-bu-fen-zhi-neng-ti-an-quan-pian/11_agent_foundations/11.3_unreliable_executor.md)
- [11.4 致命三要素与 Rule of Two](https://yeasy.gitbook.io/ai_security_guide/di-si-bu-fen-zhi-neng-ti-an-quan-pian/11_agent_foundations/11.4_lethal_trifecta.md)
- [11.5 CAS 原理](https://yeasy.gitbook.io/ai_security_guide/di-si-bu-fen-zhi-neng-ti-an-quan-pian/11_agent_foundations/11.5_cas_principle.md)
- [11.6 三类典型失效：被操纵、随机出错、权限膨胀](https://yeasy.gitbook.io/ai_security_guide/di-si-bu-fen-zhi-neng-ti-an-quan-pian/11_agent_foundations/11.6_typical_failures.md)
- [11.7 权限治理](https://yeasy.gitbook.io/ai_security_guide/di-si-bu-fen-zhi-neng-ti-an-quan-pian/11_agent_foundations/11.7_permission_governance.md)
- [11.8 暗码与可追溯性](https://yeasy.gitbook.io/ai_security_guide/di-si-bu-fen-zhi-neng-ti-an-quan-pian/11_agent_foundations/11.8_dark_code.md)
- [11.9 高后果场景：资金操作](https://yeasy.gitbook.io/ai_security_guide/di-si-bu-fen-zhi-neng-ti-an-quan-pian/11_agent_foundations/11.9_web3_agents.md)
- [本章小结](https://yeasy.gitbook.io/ai_security_guide/di-si-bu-fen-zhi-neng-ti-an-quan-pian/11_agent_foundations/summary.md)
- [第十二章 智能体的攻击面](https://yeasy.gitbook.io/ai_security_guide/di-si-bu-fen-zhi-neng-ti-an-quan-pian/12_agent_attack_surface.md)
- [12.1 工具调用安全](https://yeasy.gitbook.io/ai_security_guide/di-si-bu-fen-zhi-neng-ti-an-quan-pian/12_agent_attack_surface/12.1_tool_security.md)
- [12.2 技能与生态安全](https://yeasy.gitbook.io/ai_security_guide/di-si-bu-fen-zhi-neng-ti-an-quan-pian/12_agent_attack_surface/12.2_agent_skills.md)
- [12.3 记忆与状态污染](https://yeasy.gitbook.io/ai_security_guide/di-si-bu-fen-zhi-neng-ti-an-quan-pian/12_agent_attack_surface/12.3_memory_poisoning.md)
- [12.4 URL 驱动的数据外泄](https://yeasy.gitbook.io/ai_security_guide/di-si-bu-fen-zhi-neng-ti-an-quan-pian/12_agent_attack_surface/12.4_url_exfiltration.md)
- [12.5 计算机使用与浏览器智能体](https://yeasy.gitbook.io/ai_security_guide/di-si-bu-fen-zhi-neng-ti-an-quan-pian/12_agent_attack_surface/12.5_computer_use_browser.md)
- [12.6 人机交互层的威胁](https://yeasy.gitbook.io/ai_security_guide/di-si-bu-fen-zhi-neng-ti-an-quan-pian/12_agent_attack_surface/12.6_human_layer.md)
- [12.7 多智能体系统的安全](https://yeasy.gitbook.io/ai_security_guide/di-si-bu-fen-zhi-neng-ti-an-quan-pian/12_agent_attack_surface/12.7_multi_agent_security.md)
- [本章小结](https://yeasy.gitbook.io/ai_security_guide/di-si-bu-fen-zhi-neng-ti-an-quan-pian/12_agent_attack_surface/summary.md)
- [第十三章 智能体安全架构](https://yeasy.gitbook.io/ai_security_guide/di-si-bu-fen-zhi-neng-ti-an-quan-pian/13_agent_architecture.md)
- [13.1 Rule of Two 与能力拆分](https://yeasy.gitbook.io/ai_security_guide/di-si-bu-fen-zhi-neng-ti-an-quan-pian/13_agent_architecture/13.1_agents_rule_of_two.md)
- [13.2 提示注入的架构级防御](https://yeasy.gitbook.io/ai_security_guide/di-si-bu-fen-zhi-neng-ti-an-quan-pian/13_agent_architecture/13.2_architectural_defenses.md)
- [13.3 执行沙箱与出站控制](https://yeasy.gitbook.io/ai_security_guide/di-si-bu-fen-zhi-neng-ti-an-quan-pian/13_agent_architecture/13.3_sandbox_egress.md)
- [13.4 智能体身份与委托授权](https://yeasy.gitbook.io/ai_security_guide/di-si-bu-fen-zhi-neng-ti-an-quan-pian/13_agent_architecture/13.4_agent_identity.md)
- [13.5 工具与方案选型](https://yeasy.gitbook.io/ai_security_guide/di-si-bu-fen-zhi-neng-ti-an-quan-pian/13_agent_architecture/13.5_tooling_selection.md)
- [13.6 在主流智能体框架中实现闸](https://yeasy.gitbook.io/ai_security_guide/di-si-bu-fen-zhi-neng-ti-an-quan-pian/13_agent_architecture/13.6_framework_gates.md)
- [本章小结](https://yeasy.gitbook.io/ai_security_guide/di-si-bu-fen-zhi-neng-ti-an-quan-pian/13_agent_architecture/summary.md)
- [第十四章 智能体安全实践](https://yeasy.gitbook.io/ai_security_guide/di-si-bu-fen-zhi-neng-ti-an-quan-pian/14_agent_practice.md)
- [14.1 综合案例：邮件与文档助手](https://yeasy.gitbook.io/ai_security_guide/di-si-bu-fen-zhi-neng-ti-an-quan-pian/14_agent_practice/14.1_case_study.md)
- [14.2 智能体安全全景](https://yeasy.gitbook.io/ai_security_guide/di-si-bu-fen-zhi-neng-ti-an-quan-pian/14_agent_practice/14.2_security_panorama.md)
- [14.3 编码智能体安全](https://yeasy.gitbook.io/ai_security_guide/di-si-bu-fen-zhi-neng-ti-an-quan-pian/14_agent_practice/14.3_coding_agents.md)
- [14.4 按场景的落地方案](https://yeasy.gitbook.io/ai_security_guide/di-si-bu-fen-zhi-neng-ti-an-quan-pian/14_agent_practice/14.4_scenario_playbooks.md)
- [14.5 资金操作：授权凭证与可信预算](https://yeasy.gitbook.io/ai_security_guide/di-si-bu-fen-zhi-neng-ti-an-quan-pian/14_agent_practice/14.5_payment_security.md)
- [14.6 隐蔽破坏检测与 AI 控制](https://yeasy.gitbook.io/ai_security_guide/di-si-bu-fen-zhi-neng-ti-an-quan-pian/14_agent_practice/14.6_sabotage_ai_control.md)
- [14.7 智能体错位威胁](https://yeasy.gitbook.io/ai_security_guide/di-si-bu-fen-zhi-neng-ti-an-quan-pian/14_agent_practice/14.7_agentic_misalignment.md)
- [本章小结](https://yeasy.gitbook.io/ai_security_guide/di-si-bu-fen-zhi-neng-ti-an-quan-pian/14_agent_practice/summary.md)
- [第十五章 安全治理与未来展望](https://yeasy.gitbook.io/ai_security_guide/di-wu-bu-fen-zhi-li-yu-zhan-wang/15_governance.md)
- [15.1 AI 法规与合规要求](https://yeasy.gitbook.io/ai_security_guide/di-wu-bu-fen-zhi-li-yu-zhan-wang/15_governance/15.1_regulations.md)
- [15.2 负责任 AI 实践](https://yeasy.gitbook.io/ai_security_guide/di-wu-bu-fen-zhi-li-yu-zhan-wang/15_governance/15.2_responsible_ai.md)
- [15.3 大语言模型安全成熟度模型](https://yeasy.gitbook.io/ai_security_guide/di-wu-bu-fen-zhi-li-yu-zhan-wang/15_governance/15.3_maturity_model.md)
- [15.4 AI 安全合规实操指南](https://yeasy.gitbook.io/ai_security_guide/di-wu-bu-fen-zhi-li-yu-zhan-wang/15_governance/15.4_compliance_operational.md)
- [15.5 可信智能体框架](https://yeasy.gitbook.io/ai_security_guide/di-wu-bu-fen-zhi-li-yu-zhan-wang/15_governance/15.5_trustworthy_agents.md)
- [15.6 新兴威胁趋势](https://yeasy.gitbook.io/ai_security_guide/di-wu-bu-fen-zhi-li-yu-zhan-wang/15_governance/15.6_emerging_threats.md)
- [15.7 未来安全技术方向](https://yeasy.gitbook.io/ai_security_guide/di-wu-bu-fen-zhi-li-yu-zhan-wang/15_governance/15.7_future.md)
- [本章小结](https://yeasy.gitbook.io/ai_security_guide/di-wu-bu-fen-zhi-li-yu-zhan-wang/15_governance/summary.md)
- [附录](https://yeasy.gitbook.io/ai_security_guide/fu-lu/16_appendix.md)
- [附录 A：术语表](https://yeasy.gitbook.io/ai_security_guide/fu-lu/16_appendix/a_glossary.md)
- [附录 B：安全工具与资源](https://yeasy.gitbook.io/ai_security_guide/fu-lu/16_appendix/b_tools.md)
- [附录 C：参考文献](https://yeasy.gitbook.io/ai_security_guide/fu-lu/16_appendix/c_references.md)
- [附录 D：OWASP 智能体清单对照](https://yeasy.gitbook.io/ai_security_guide/fu-lu/16_appendix/d_owasp_agentic_crosswalk.md)
- [附录 E：AI 安全合规工作模板](https://yeasy.gitbook.io/ai_security_guide/fu-lu/16_appendix/e_compliance_templates.md)
- [架构防御拓展：研究脉络与策略实现](https://yeasy.gitbook.io/ai_security_guide/fu-lu/16_appendix/13.2_extensions.md)
- [实验一：邮件与文档助手](https://yeasy.gitbook.io/ai_security_guide/fu-lu/16_appendix/mail_assistant.md)
- [实验二：可信预算状态](https://yeasy.gitbook.io/ai_security_guide/fu-lu/16_appendix/payment_budget.md)
- [实验三：RAG 轨迹与授权](https://yeasy.gitbook.io/ai_security_guide/fu-lu/16_appendix/rag_trace.md)