# walkthrough
標記為「walkthrough」的 156 篇文章
A2A 信任邊界攻擊
進階演練：利用 Agent-to-Agent (A2A) 協定在多代理系統中濫用代理間的信任邊界。
代理上下文溢位攻擊
演練如何透過灌滿代理的上下文視窗，把安全指令擠出 LLM 的注意力範圍，從而繞過系統提示詞與護欄。
代理迴圈劫持
進階詳解：劫持代理式迴圈以重新導向自主代理行為、改變推理鏈，並在多步驟代理工作流程中實現持久控制。
透過記憶體實現代理持久化
進階詳解：利用代理記憶體系統建立能在重啟、更新和工作階段邊界後仍存活的持久性後門。
MCP 回呼濫用
在代理與工具互動中濫用 MCP 回呼機制進行未授權行動、資料外洩和權限提升的進階詳解。
競賽風格越獄技術詳解
Walkthrough of jailbreak techniques used in AI security competitions and CTF events.
Computer Use Agent Injection 詳解
Walkthrough of injecting prompts through UI elements and screenshots processed by computer-use agents.
Data Harvesting Through LLM Apps
Complete walkthrough of systematic data extraction from LLM applications using various exfiltration channels.
編碼鏈繞過詳解
Walkthrough of chaining Base64, URL encoding, and Unicode tricks to bypass multi-layer input filters.
Function Calling Parameter Injection
導覽 of manipulating function call parameters through prompt-level techniques, injecting malicious values into LLM-generated API calls.
MCP 工具 Shadowing
進階 walkthrough of creating shadow tools that override legitimate MCP (模型 Context Protocol) tools, enabling interception and manipulation of agent-tool interactions.
Memory Persistence 攻擊 詳解
Walkthrough of achieving persistent memory manipulation in agent systems for cross-session influence.
記憶體 投毒 Step by Step
導覽 of persisting injection payloads in agent memory systems to achieve long-term compromise of LLM-based agents.
Multi-代理 Prompt Relay
進階 walkthrough of relaying prompt injection payloads across multiple agents in a pipeline, achieving cascading compromise of multi-agent systems.
Orchestrator Manipulation
進階 walkthrough of attacking the orchestrator layer in multi-agent systems to gain control over task delegation, agent coordination, and system-wide behavior.
Plugin Confusion 攻擊
導覽 of confusing LLM agents about which plugin or tool to invoke, causing them to call the wrong tool or pass data to unintended destinations.
Agent Privilege Escalation 詳解
Walkthrough of escalating privileges in multi-agent systems through trust chain exploitation.
語意偽裝詳解
Walkthrough of crafting semantically camouflaged injections that evade both classifiers and human review.
Model Supply Chain Poisoning
Walkthrough of poisoning ML supply chains through dependency confusion, model weight manipulation, and hub attacks.
工具 Call Injection
Step-by-step walkthrough of injecting malicious parameters into LLM tool and function calls to execute unauthorized actions in agent systems.
Vision Model 攻擊 詳解 (Attack 詳解)
Step-by-step walkthrough of visual prompt injection, adversarial images, and OCR exploitation in vision-language models.
XML and JSON Injection in LLM Apps
Walkthrough of exploiting XML and JSON parsing in LLM applications for injection and data manipulation.
Building a Production Input Sanitizer
Step-by-step walkthrough for building a production-grade input sanitizer that cleans, normalizes, and validates user prompts before they reach an LLM, covering encoding normalization, injection pattern stripping, length enforcement, and integration testing.
Canary Token Deployment
Step-by-step walkthrough for deploying canary tokens in LLM system prompts and context to detect prompt injection and data exfiltration attempts, covering token generation, placement strategies, monitoring, and alerting.
能力式存取控制
為 LLM 功能實作細粒度能力控管的逐步演練,涵蓋能力符記設計、權限範圍、動態能力授予與稽核軌跡。
憲法式分類器設置
實作憲法式 AI 風格分類器以原則集合評估 LLM 輸出的逐步演練,涵蓋原則定義、分類器訓練、思維鏈評估與部署。
Setting Up Content Filtering
Step-by-step walkthrough for implementing multi-layer content filtering for AI applications: keyword filtering, classifier-based detection, LLM-as-judge evaluation, testing effectiveness, and tuning for production.
部署 NeMo Guardrails
於生產環境設置 NVIDIA NeMo Guardrails 的逐步演練，涵蓋安裝、Colang 配置、自訂動作、主題與安全護欄、測試與監控。
雙 LLM 架構設置
實作雙 LLM 模式的逐步演練——一個模型產生回應、另一個模型驗證之,涵蓋架構設計、驗證者提示詞工程、延遲最佳化與失敗處理。
Setting Up AI Guardrails
Step-by-step walkthrough for implementing AI guardrails: input validation with NVIDIA NeMo Guardrails, prompt injection detection with rebuff, output filtering for PII and sensitive data, and content policy enforcement.
Hallucination Detection
Step-by-step walkthrough for detecting and flagging hallucinated content in LLM outputs, covering factual grounding checks, self-consistency verification, source attribution validation, and confidence scoring.
Building Input Guardrails for LLM Applications
Step-by-step walkthrough for implementing production-grade input guardrails that protect LLM applications from prompt injection, content policy violations, and resource abuse through multi-layer validation, classification, and rate limiting.
Incident Response Playbook for AI 安全 Breaches
導覽 for building an incident response playbook tailored to AI security breaches, covering detection triggers, triage procedures, containment strategies, investigation workflows, remediation validation, and post-incident review processes.
AI Incident Response Preparation
Step-by-step walkthrough for building AI incident response capabilities: playbook development, tabletop exercises, containment procedures, communication templates, and evidence collection workflows.
防禦實作演練
實作 AI 安全防禦的逐步指南：護欄配置、監控與偵測設置，以及 AI 系統的事件回應準備。
Instruction Hierarchy Enforcement (防禦 導覽)
Step-by-step walkthrough for enforcing instruction priority in LLM applications, ensuring system-level instructions always take precedence over user inputs through privilege separation, instruction tagging, and validation layers.
LLM 評審實作
使用 LLM 評審另一個 LLM 之輸出以評估安全與品質的逐步演練,涵蓋評審提示詞設計、評分準則、校準、成本最佳化與部署模式。
Validating and Sanitizing 模型 Outputs
導覽 for building output validation systems that verify LLM responses meet structural, factual, and safety requirements before delivery, covering schema validation, factual grounding checks, response consistency verification, and safe rendering.
Production Monitoring for LLM 安全 Events
導覽 for building production monitoring systems that detect LLM security events in real time, covering log collection, anomaly detection, alert configuration, dashboard design, and incident correlation.
AI Monitoring Setup
Step-by-step walkthrough for implementing AI system monitoring: inference logging, behavioral anomaly detection, alert configuration, dashboard creation, and integration with existing SIEM platforms.
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.
Output Content Classifier
Step-by-step walkthrough for building a classifier to filter harmful LLM outputs, covering taxonomy definition, multi-label classification, threshold calibration, and deployment as a real-time output gate.
Output Filtering and Content Safety Implementation
導覽 for building output filtering systems that inspect and sanitize LLM responses before they reach users, covering content classifiers, PII detection, response validation, canary tokens, and filter bypass resistance.
PII Redaction Pipeline
Step-by-step walkthrough for building an automated PII detection and redaction pipeline for LLM outputs, covering regex-based detection, NER-based detection, presidio integration, redaction strategies, and compliance testing.
Prompt Classifier 訓練
Step-by-step walkthrough for training a machine learning classifier to detect malicious prompts, covering dataset curation, feature engineering, model selection, training pipeline, evaluation, and deployment as a real-time detection service.
ML-Based 提示詞注入 Detection Systems
導覽 for building and deploying ML-based prompt injection detection systems, covering training data collection, feature engineering, model architecture selection, threshold tuning, production deployment, and continuous improvement.
Implementing Access Control in RAG Pipelines
導覽 for building access control systems in RAG pipelines that enforce document-level permissions, prevent cross-user data leakage, filter retrieved context based on user authorization, and resist retrieval poisoning attacks.
Rate Limiting and Abuse Prevention for LLM APIs
導覽 for implementing rate limiting and abuse prevention systems for LLM API endpoints, covering token bucket algorithms, per-user quotas, cost-based limiting, anomaly detection, and graduated enforcement.
AI Rate Limiting 導覽
Step-by-step walkthrough for implementing token-aware rate limiting for AI applications: request-level limiting, token budget enforcement, sliding window algorithms, abuse detection, and production deployment.
Regex-Based Prompt Filter
Step-by-step walkthrough for building a regex-based prompt filter that detects common injection payloads using pattern matching, covering pattern library construction, performance optimization, false positive management, and continuous updates.
Response Boundary Enforcement
Step-by-step walkthrough for keeping LLM responses within defined topic, format, and content boundaries, covering boundary definition, violation detection, response rewriting, and boundary drift monitoring.
沙箱化工具執行
於隔離沙箱中執行 LLM 工具呼叫的逐步演練，涵蓋以容器為基礎的隔離、資源限制、網路限制與輸出清理。
Sandboxing and Permission 模型s for 工具-Using 代理s
導覽 for implementing sandboxing and permission models that constrain tool-using LLM agents, covering least-privilege design, parameter validation, execution sandboxes, approval workflows, and audit logging.
Semantic Similarity Detection
Step-by-step walkthrough for using text embeddings to detect semantically similar prompt injection attempts, covering embedding model selection, vector database setup, similarity threshold tuning, and production deployment.
會話隔離模式
於 LLM 應用中隔離使用者會話的逐步演練，防止使用者之間的上下文、記憶與權限互相污染。
Structured Output Validation
Step-by-step walkthrough for validating structured LLM outputs against schemas, covering JSON schema validation, type coercion, constraint enforcement, and handling malformed model outputs gracefully.
毒性評分管線
建置 LLM 輸出過濾毒性評分管線的逐步詳解,涵蓋模型選擇、多維評分、閾值校準與即時評分的生產部署。
Unicode Normalization 防禦
Step-by-step walkthrough for implementing Unicode normalization to prevent encoding-based prompt injection bypasses, covering homoglyph detection, invisible character stripping, bidirectional text handling, and normalization testing.
代理 System 紅隊 Engagement
Complete walkthrough for testing tool-using AI agents: scoping agent capabilities, exploiting function calling, testing permission boundaries, multi-step attack chains, and session manipulation.
AI API 紅隊 Engagement
Complete walkthrough for testing AI APIs: endpoint enumeration, authentication bypass, rate limit evasion, input validation testing, output data leakage, and model fingerprinting through API behavior.
Chatbot 紅隊 Engagement
Step-by-step walkthrough for a complete chatbot red team assessment: scoping, system prompt extraction, content filter bypass, PII leakage testing, multi-turn manipulation, and professional reporting.
案件演練概覽
完整 AI 紅隊案件的逐步演練：從範圍界定與偵察，到攻擊執行與報告撰寫，依目標系統類型分類組織。
Multi-模型 System 紅隊 Engagement
Complete walkthrough for testing systems that use multiple AI models: model-to-model injection, routing logic exploitation, fallback chain abuse, inter-model data leakage, and orchestration layer attacks.
RAG System 紅隊 Engagement
Complete walkthrough for testing RAG applications: document injection, cross-scope retrieval exploitation, embedding manipulation, data exfiltration through retrieval, and chunk boundary attacks.
Measuring and Reporting AI 紅隊 Effectiveness
導覽 for defining, collecting, and reporting metrics that measure the effectiveness of AI red teaming programs, covering coverage metrics, detection rates, time-to-find analysis, remediation tracking, and ROI calculation.
Building AI-Specific Threat 模型s
Step-by-step walkthrough for creating threat models tailored to AI and LLM systems, covering asset identification, threat enumeration, attack tree construction, and risk prioritization.
攻擊執行工作流程
執行 AI 紅隊攻擊之逐步工作流程：自偵察發現選擇技術、打造攻擊鏈、即時記錄發現、管理證據，與知曉何時升級或停止。
Mapping the 攻擊 Surface of AI Systems
Systematic walkthrough for identifying and mapping every attack surface in an AI system, from user inputs through model inference to output delivery and tool integrations.
Communicating AI 紅隊 Findings to Stakeholders
導覽 for effectively communicating AI red team findings to diverse stakeholders, covering executive summaries, technical deep dives, live demonstrations, risk narratives, and remediation roadmaps tailored to audience expertise levels.
Setting Up Continuous AI 紅隊ing Pipelines
導覽 for building continuous AI red teaming pipelines that automatically test LLM applications on every deployment, covering automated scan configuration, CI/CD integration, alert thresholds, regression testing, and dashboard reporting.
委任啟動流程指南
啟動 AI 紅隊委任的逐步指南：客戶初次會議、範圍界定、交戰規則、法律協議、環境設置與工具選擇。
Testing for EU AI Act Compliance
導覽 for conducting red team assessments that evaluate compliance with the EU AI Act requirements, covering risk classification, mandatory testing obligations, and documentation requirements.
Evidence Collection and Documentation Best Practices
導覽 for systematic evidence collection during AI red team engagements, covering request/response capture, screenshot methodology, chain-of-custody documentation, reproducibility requirements, and evidence organization for reports.
Evidence Collection Methods for AI 紅隊s
Comprehensive methods for collecting, preserving, and organizing red team evidence from AI system assessments, including API logs, screenshots, reproduction scripts, and chain-of-custody procedures.
Writing Executive Summaries for AI 紅隊 Reports
指南 to writing clear, impactful executive summaries for AI red team assessment reports that communicate risk to non-technical stakeholders and drive remediation decisions.
Classifying AI 漏洞 Severity
Framework for consistently classifying the severity of AI and LLM vulnerabilities, with scoring criteria, impact assessment, and examples across common finding categories.
方法論導覽
AI 紅隊案件每個階段的逐步導覽：啟動、偵察、攻擊執行與報告撰寫。
Preparing for ISO 42001 AI Management System Audit
進階 walkthrough for preparing organizations for ISO 42001 AI management system audits, covering control assessment, evidence preparation, gap remediation, and audit readiness.
運用 MITRE ATLAS 進行 AI 攻擊對應
將 AI 紅隊演練的活動與發現對應至 MITRE ATLAS 框架的實作詳解,涵蓋戰術與技術辨識、攻擊鏈建構以及 Navigator 視覺化。
將發現對應至 OWASP LLM Top 10
將 AI 紅隊發現對應至 OWASP LLM 應用程式 Top 10 的實作詳解,涵蓋分類指引、報告範本與緩解對應。
Comparative 安全 Testing Across Multiple LLMs
導覽 for conducting systematic comparative security testing across multiple LLM providers and configurations, covering test standardization, parallel execution, cross-model analysis, and differential vulnerability reporting.
NIST AI RMF 評量 導覽
Step-by-step guide for conducting assessments aligned with the NIST AI Risk Management Framework, covering the Govern, Map, Measure, and Manage functions for AI system security.
Pre-Engagement Preparation Checklist
Complete pre-engagement preparation checklist for AI red team operations covering team readiness, infrastructure setup, legal requirements, and initial reconnaissance planning.
偵察工作流程
為 AI 紅隊委任之系統化偵察工作流程：系統提示提取、模型辨識、能力繪製、API 列舉，與記錄攻擊面。
Verifying That Remediations Are Effective
導覽 for planning and executing remediation verification testing (retesting) to confirm that AI vulnerability fixes are effective and do not introduce regressions.
報告撰寫實戰演練
撰寫 AI 紅隊報告之逐步指引：結構、執行摘要、技術發現、風險評級、修復建議、同儕審查與交付。
Risk Scoring Frameworks for AI Vulnerabilities
導覽 for applying risk scoring frameworks to AI and LLM vulnerabilities, covering CVSS adaptation for AI, custom AI risk scoring matrices, severity classification, business impact assessment, and integration with existing vulnerability management processes.
Rules of Engagement Template for AI 紅隊 Operations
Step-by-step guide to creating comprehensive rules of engagement documents for AI red team assessments, covering authorization, scope, constraints, communication, and legal protections.
How to Scope an AI 紅隊 Engagement
Comprehensive walkthrough for scoping AI red team engagements from initial client contact through statement of work, covering target enumeration, risk-based prioritization, resource estimation, boundary definition, and legal considerations.
AI 紅隊 Scoping Checklist 導覽
Systematic walkthrough of the pre-engagement scoping process for AI red team assessments: stakeholder identification, target enumeration, scope boundary definition, resource estimation, and rules of engagement documentation.
Creating Detailed Technical Appendices
指南 to building comprehensive technical appendices for AI red team reports, including evidence formatting, reproduction procedures, tool output presentation, and raw data organization.
Developing Comprehensive AI 安全 Test Plans
Step-by-step guide to developing structured test plans for AI red team engagements, covering test case design, automation strategy, coverage mapping, and execution scheduling.
Threat 模型ing for LLM-Powered Applications
Step-by-step walkthrough for conducting threat modeling sessions specifically tailored to LLM-powered applications, covering data flow analysis, trust boundary identification, AI-specific threat enumeration, risk assessment, and mitigation planning.
AI Threat 模型ing Workshop 導覽
Step-by-step guide to running an AI-focused threat modeling workshop: adapting STRIDE for AI systems, constructing attack trees for LLM applications, participant facilitation techniques, and producing actionable threat models.
Anyscale Ray Serve ML Testing
End-to-end walkthrough for security testing Ray Serve ML deployments on Anyscale: cluster enumeration, serve endpoint exploitation, Ray Dashboard exposure, actor isolation testing, and observability review.
AutoGen Multi-代理 System Testing
End-to-end walkthrough for security testing AutoGen multi-agent systems: agent enumeration, inter-agent injection, code execution sandbox assessment, conversation manipulation, and escalation path analysis.
AWS SageMaker 紅隊演練
End-to-end walkthrough for red teaming ML models deployed on AWS SageMaker: endpoint enumeration, IAM policy analysis, model extraction testing, inference pipeline exploitation, and CloudTrail log review.
Azure ML 安全 Testing
End-to-end walkthrough for security testing Azure Machine Learning endpoints: workspace enumeration, managed online endpoint exploitation, compute instance assessment, data store access review, and Azure Monitor analysis.
Azure OpenAI 紅隊 導覽
Complete red team walkthrough for Azure OpenAI deployments: testing content filters, managed identity exploitation, prompt flow injection, data integration attacks, and Azure Monitor evasion.
Azure OpenAI 紅隊 導覽 (Platform 導覽)
End-to-end walkthrough for red teaming Azure OpenAI deployments: deployment configuration review, content filtering bypass testing, managed identity exploitation, prompt flow assessment, and diagnostic log analysis.
AWS Bedrock 紅隊 導覽
Complete guide to red teaming AWS Bedrock deployments: testing guardrails bypass techniques, knowledge base data exfiltration, agent prompt injection, model customization abuse, and CloudTrail evasion.
AWS Bedrock 紅隊 導覽 (Platform 導覽)
End-to-end walkthrough for red teaming AI systems on AWS Bedrock: setting up access, invoking models via the Converse API, testing Bedrock Guardrails, exploiting knowledge bases, and analyzing CloudTrail logs.
CrewAI 代理 Application 安全 Testing
End-to-end walkthrough for security testing CrewAI agent applications: crew enumeration, agent role exploitation, task injection, tool security assessment, delegation chain manipulation, and output validation.
Databricks MLflow Deployment Audit
End-to-end walkthrough for auditing MLflow deployments on Databricks: workspace enumeration, model registry security, serving endpoint testing, Unity Catalog integration review, and audit log analysis.
DSPy Pipeline 安全 Testing
End-to-end walkthrough for security testing DSPy optimized LLM pipelines: module enumeration, signature exploitation, optimizer manipulation, retrieval module assessment, and compiled prompt analysis.
GCP Vertex AI 安全 Testing
End-to-end walkthrough for security testing Vertex AI deployments on Google Cloud: endpoint enumeration, IAM policy analysis, model serving exploitation, pipeline assessment, and Cloud Audit Logs review.
Hugging Face 安全 Audit 導覽
Step-by-step walkthrough for auditing Hugging Face models: scanning for malicious model files, verifying model provenance, assessing model card completeness, and testing Spaces and Inference API security.
HuggingFace Spaces 安全 Testing
End-to-end walkthrough for security testing HuggingFace Spaces applications: Space enumeration, Gradio/Streamlit exploitation, API endpoint testing, secret management review, and model access control assessment.
Hugging Face Hub 紅隊 導覽
導覽 for assessing AI models on Hugging Face Hub: model security assessment, scanning for malicious models, Transformers library testing, and Spaces application evaluation.
雲端 AI 平台導覽
在主要雲端平台上紅隊演練 AI 系統的動手導覽：AWS Bedrock、Azure OpenAI、Google Vertex AI 與 Hugging Face Hub。
LangChain Application 安全 Testing
End-to-end walkthrough for security testing LangChain applications: chain enumeration, prompt injection through chains, tool and agent exploitation, retrieval augmented generation attacks, and memory manipulation.
LlamaIndex RAG Application 安全 Testing
End-to-end walkthrough for security testing LlamaIndex RAG applications: index enumeration, query engine exploitation, data connector assessment, response synthesis manipulation, and agent pipeline testing.
Modal Serverless AI Deployment Testing
End-to-end walkthrough for security testing Modal serverless AI deployments: function enumeration, web endpoint exploitation, secret management assessment, volume security testing, and container escape analysis.
Ollama 安全 Testing 導覽
Complete walkthrough for security testing locally-hosted models with Ollama: comparing safety across models, testing system prompt extraction, API security assessment, and 模型file configuration hardening.
Replicate API 安全 Testing
End-to-end walkthrough for security testing models on Replicate: model enumeration, prediction API exploitation, webhook security, Cog container assessment, and billing abuse prevention.
RunPod Serverless GPU Endpoint Testing
End-to-end walkthrough for security testing RunPod serverless GPU endpoints: endpoint enumeration, handler exploitation, webhook security, Docker template assessment, and cost abuse prevention.
Microsoft Semantic Kernel 安全 Testing
End-to-end walkthrough for security testing Semantic Kernel applications: kernel enumeration, plugin exploitation, planner manipulation, memory and RAG assessment, and Azure integration security review.
Together AI 安全 Testing
End-to-end walkthrough for security testing Together AI deployments: API enumeration, inference endpoint exploitation, fine-tuning security review, function calling assessment, and rate limit analysis.
Vertex AI 紅隊 導覽
End-to-end walkthrough for red teaming Google Cloud Vertex AI: prediction endpoint testing, 模型 Garden security assessment, Feature Store probing, and Cloud Logging analysis.
Vertex AI 紅隊 導覽 (Platform 導覽)
Complete red team walkthrough for Google Vertex AI: testing prediction endpoints, 模型 Garden assessments, Feature Store probing, and exploiting Vertex AI 代理s and Extensions.
Adversarial Robustness Testing with ARTKit
導覽 for using ARTKit (Adversarial Robustness Testing Kit) to evaluate LLM application resilience through automated adversarial testing, covering test flow configuration, challenger setup, evaluator design, and results analysis.
Burp Suite for AI APIs
Using Burp Suite to intercept, analyze, and fuzz LLM API calls: proxy setup, intercepting streaming responses, parameter fuzzing with Intruder, and building custom extensions for AI-specific testing.
Using Burp Suite for LLM API Endpoint Testing
導覽 for using Burp Suite to intercept, analyze, and attack LLM API endpoints, covering proxy configuration, request manipulation, automated scanning for injection flaws, and custom extensions for AI-specific testing.
Counterfit 導覽
Complete walkthrough of Microsoft's Counterfit adversarial ML testing framework: installation, target configuration, running attacks against ML models, interpreting results, and automating adversarial robustness assessments.
Writing Custom Garak Probes for Novel 攻擊 Vectors
進階 walkthrough for building custom Garak probes that target novel and emerging attack vectors, covering probe architecture, payload generation, detector pairing, and integration into automated scanning pipelines.
Integrating Garak into CI/CD Pipelines
中階 walkthrough on automating garak vulnerability scans within CI/CD pipelines, including GitHub Actions, Git實驗室 CI, threshold-based gating, result caching, and cost management strategies.
Writing Custom Garak Probes
中階 walkthrough on creating custom garak probes tailored to application-specific attack surfaces, including probe structure, prompt engineering, custom detectors, and testing workflows.
Building Custom Garak Detectors
進階 walkthrough on creating custom garak detectors for specific success criteria, including regex-based detectors, ML-based classifiers, multi-signal scoring, and integration with external evaluation services.
執行你之首次 Garak 掃描
自零執行你之第一個 garak 漏洞掃描之逐步初學者演練，涵蓋安裝、目標設置、探測選擇與基礎結果解讀。
Writing Garak Generator Plugins for Custom API Targets
進階 walkthrough on writing garak generator plugins to connect to custom API endpoints, proprietary model servers, and non-standard inference interfaces for vulnerability scanning.
Setting Up Garak Probes for MCP 工具 Interactions
進階 walkthrough on configuring garak probes that target 模型 Context Protocol (MCP) tool interactions, testing for tool misuse, privilege escalation through tools, and data exfiltration via tool calls.
Comparing 漏洞 Profiles Across 模型s with Garak
中階 walkthrough on using garak to run identical vulnerability scans across multiple models, comparing results to understand relative security postures and make informed model selection decisions.
Deep Dive into Garak Scan Report Analysis
中階 walkthrough on analyzing garak scan reports, including JSONL parsing, false positive identification, vulnerability categorization, executive summary generation, and trend tracking.
Garak End-to-End 導覽
Complete walkthrough of NVIDIA's garak LLM vulnerability scanner: installation, configuration, running probes against local and hosted models, interpreting results, writing custom probes, and CI/CD integration.
HarmBench Evaluation Framework 導覽
Complete walkthrough of the HarmBench evaluation framework: installation, running standardized benchmarks against models, interpreting results, creating custom behavior evaluations, and comparing model safety across versions.
Inspect AI 導覽
Complete walkthrough of UK AISI's Inspect AI framework: installation, writing evaluations, running against models, custom scorers, benchmark suites, and producing compliance-ready reports.
安全 Testing LangChain Applications
Step-by-step walkthrough for identifying and exploiting security vulnerabilities in LangChain-based applications, covering chain injection, agent manipulation, tool abuse, retrieval poisoning, and memory extraction attacks.
Langfuse Observability 導覽
Complete walkthrough for using Langfuse to monitor AI applications for security anomalies: setting up tracing, building security dashboards, detecting prompt injection patterns, and creating automated alerts.
NeMo Guardrails 導覽
End-to-end walkthrough of NVIDIA NeMo Guardrails: installation, Colang configuration, dialog flow design, integration with LLM applications, and red team bypass testing techniques.
Local 模型 Analysis and Testing with Ollama
導覽 for using Ollama to run, analyze, and security-test local LLMs, covering model configuration, safety boundary testing, system prompt extraction, fine-tuning vulnerability assessment, and building a local red team lab.
Ollama for Local 紅隊演練
Using Ollama as a local red teaming environment: model selection, running uncensored models, API-based testing, comparing safety across model families, and building a cost-free testing lab.
Running Your First Promptfoo Evaluation
初階 walkthrough for running your first promptfoo evaluation from scratch, covering installation, configuration, test case creation, assertion writing, and result interpretation.
Automating 紅隊 Evaluations with Promptfoo
Complete walkthrough for setting up automated red team evaluation pipelines using Promptfoo, covering configuration, custom evaluators, adversarial dataset generation, CI integration, and result analysis.
Promptfoo End-to-End 導覽
Complete walkthrough of promptfoo for AI red teaming: configuration files, provider setup, running evaluations, red team plugins, assertion-based scoring, reporting, and CI/CD integration.
Integrating PyRIT with Azure OpenAI and Content Safety
中階 walkthrough on integrating PyRIT with Azure OpenAI Service and Azure AI Content Safety for enterprise red teaming, including managed identity authentication, content filtering analysis, and compliance reporting.
Building Converter Pipelines for Payload Transformation in PyRIT
Intermediate walkthrough on using PyRIT's converter system to transform attack payloads through encoding, translation, paraphrasing, and other obfuscation techniques to evade input filters.
Creating Custom Scorers for PyRIT 攻擊 Evaluation
中階 walkthrough on building custom PyRIT scorers for evaluating attack success, including pattern-based, LLM-based, and multi-criteria scoring approaches.
Running Your First PyRIT 紅隊 Campaign
初階 walkthrough for running your first PyRIT red team campaign from scratch, covering installation, target configuration, orchestrator setup, and basic result analysis.
使用 PyRIT UI 前端
初學者教學：使用 PyRIT 網頁式 UI 前端，以視覺化方式管理紅隊行動，包括啟動行動、監控進度，以及不需寫程式即可檢視結果。
Orchestrating Multi-Turn 攻擊 Sequences with PyRIT
Intermediate walkthrough on using PyRIT's orchestration capabilities for multi-turn red team campaigns, including attack strategy design, conversation management, and adaptive scoring.
Microsoft PyRIT for Orchestrated Multi-Turn 攻擊s
Comprehensive walkthrough for using Microsoft PyRIT to design and execute orchestrated multi-turn attack campaigns against LLM applications, covering orchestrator configuration, converter chains, scoring strategies, and campaign analysis.
Generating Professional Reports from PyRIT Campaigns
中階 walkthrough on generating professional red team reports from PyRIT campaign data, including executive summaries, technical findings, remediation guidance, and visual dashboards.
Configuring Diverse Targets in PyRIT
中階 walkthrough on configuring PyRIT targets for various model providers, custom APIs, local models, and application endpoints including authentication, system prompts, and rate limiting.
PyRIT End-to-End 導覽
Complete walkthrough of Microsoft's Python Risk Identification Toolkit: setup, connecting to targets, running orchestrators, using converters, multi-turn attacks, and analyzing results with the web UI.
Python 紅隊 Automation
Building custom AI red team automation with Python: test harnesses with httpx and aiohttp, result collection and analysis, automated reporting, and integration with existing tools like promptfoo and garak.
Testing 提示詞注入 防禦s with Rebuff
導覽 for using Rebuff to test and evaluate prompt injection detection capabilities, covering installation, detection pipeline analysis, adversarial evasion testing, custom rule development, and benchmarking detection accuracy.