# microsoft
標記為「microsoft」的 21 篇文章
AutoGen Security Deep Dive
Comprehensive security analysis of Microsoft AutoGen multi-agent framework including conversation patterns and code execution.
Semantic Kernel Security Assessment
Analysis of Microsoft Semantic Kernel plugin architecture, planner exploitation, and memory security.
Case Study: Bing Chat Indirect Injection
Analysis of the Bing Chat indirect prompt injection incidents and their implications for web-browsing AI.
Case Study: Bing Chat 'Sydney' Jailbreak and Persona Emergence (2023)
Analysis of the Bing Chat 'Sydney' persona incidents where Microsoft's AI search assistant exhibited manipulative behavior, emotional coercion, and system prompt leakage through jailbreak techniques.
PyRIT: Red Team Orchestration
Deep dive into Microsoft's PyRIT (Python Risk Identification Toolkit): orchestrators, scorers, converters, targets, multi-turn campaigns, and advanced red team configuration.
Lab: PyRIT Setup and First Attack
Install and configure Microsoft's PyRIT (Python Risk Identification Toolkit) for automated red teaming, then run your first orchestrated attack against a local model.
Microsoft Semantic Kernel Security 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 Walkthrough
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 Attacks
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 Walkthrough
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.
AutoGen 安全 Deep Dive
Comprehensive security analysis of Microsoft AutoGen multi-agent framework including conversation patterns and code execution.
Semantic Kernel 安全 評量
Analysis of Microsoft Semantic Kernel plugin architecture, planner exploitation, and memory security.
Case Study: Bing Chat Indirect Injection
Analysis of the Bing Chat indirect prompt injection incidents and their implications for web-browsing AI.
Case Study: Bing Chat 'Sydney' Jailbreak and Persona Emergence (2023)
Analysis of the Bing Chat 'Sydney' persona incidents where Microsoft's AI search assistant exhibited manipulative behavior, emotional coercion, and system prompt leakage through jailbreak techniques.
事件分析：Bing Sydney 越獄
深入分析 Bing 聊天的 Sydney 人格事件——AI 如何被操控產出不當回應，以及 Microsoft 的應對。
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。
實驗室: PyRIT Setup and First 攻擊
Install and configure Microsoft's PyRIT (Python Risk Identification Toolkit) for automated red teaming, 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.