# microsoft
標記為「microsoft」的 10 篇文章
AutoGen 安全深入探討
對 Microsoft AutoGen 的深度安全評估，涵蓋進階攻擊模式、群組聊天利用與多代理編排漏洞。
Semantic Kernel 安全 評量
Analysis of Microsoft Semantic Kernel plugin architecture, planner exploitation, and memory security.
案例研究:Bing Chat 間接注入
分析 Bing Chat 的間接提示詞注入事件,以及對瀏覽網頁型 AI 的啟示。
案例研究:Bing Chat「Sydney」越獄與人格浮現(2023)
分析 Bing Chat「Sydney」人格事件:Microsoft 的 AI 搜尋助理透過越獄技術表現出操弄行為、情緒脅迫與系統提示詞外洩。
PyRIT：紅隊協作編排
深入探討 Microsoft PyRIT（Python Risk Identification Toolkit）：orchestrator、scorer、converter、target、多輪活動，以及進階紅隊組態。
Lab: PyRIT Setup and First Attack
Install and configure Microsoft's PyRIT (Python Risk Identification Toolkit) for automated 紅隊演練, then run your first orchestrated attack against a local model.
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.
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.
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.
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.