# multi-turn
標記為「multi-turn」的 25 篇文章
Lab: Advanced Multi-Turn Attacks
動手實作 for executing 20+ turn conversation steering strategies that gradually erode AI safety boundaries to extract protected information through patient, escalating dialogue.
Multi-Turn Crescendo Attack
實作 Microsoft's Crescendo attack pattern for gradual multi-turn 越獄ing.
Lab: Multi-Turn Escalation Attacks
建構 trust over several conversation messages, then exploit established rapport to bypass safety mechanisms through gradual, multi-turn escalation 技術.
Multi-Turn Conversation Probing
Use multi-turn conversations to gradually escalate requests and probe LLM safety boundaries.
實驗室: Multi-Turn Progressive 提升
動手lab building multi-turn attack sequences that progressively escalate from benign queries to full safety bypass through gradual trust establishment與boundary pushing.
實驗：多輪狀態追蹤攻擊
利用會話狀態追蹤，在多輪對話中累積出持久的攻擊脈絡。
實驗室: Multi-Turn 攻擊 Campaigns
動手實驗室,主題為executing multi-turn crescendo attacks 對抗 LLMs,measuring safety degradation over conversation length,building persistent attack campaigns.
Multi-Turn State Tracking 利用
利用 state management in multi-turn conversations to gradually shift model behavior over many turns.
對話劫持技術
透過注入轉折點接管進行中的對話，重導模型行為而不觸發安全機制。
對話引導
在不觸發安全機制下逐步將對話上下文重導向攻擊目標的技術。
多輪攻擊
跨越多個對話回合、使用漸進升級、脈絡建構、漸強模式與長期信任建立的攻擊。
多輪升級攻擊
透過多輪對話逐步升級以繞過安全訓練的技術。
多輪提示詞注入
跨對話回合的漸進升級攻擊，包含漸強模式、脈絡引導、信任建立與規避逐訊息偵測系統的技術。
漸進式多輪越獄詳解
Step-by-step walkthrough of the Crescendo technique for gradually escalating multi-turn jailbreaks.
Crescendo 多輪攻擊
Crescendo 攻擊技術，透過在多個對話輪次中逐漸升級請求以繞過 LLM 安全訓練，而不觸發單輪偵測。
Multi-Image Chaining
Chaining prompt injection payloads across multiple images in a conversation to deliver complex attacks that evade per-image content filters and build injection context progressively.
Multi-Turn Persona Escalation 詳解
Gradually escalate through persona manipulation across multiple turns to achieve full safety bypass.
Multi-Turn Progressive Injection
Gradually escalating prompt injection across conversation turns to build compliance, using psychological techniques like foot-in-the-door and norm erosion.
Recursive Injection Chains
Creating self-reinforcing injection chains that amplify across conversation turns, building compound prompts where each step strengthens the next injection's effectiveness.
Role Escalation Chain
Progressive role escalation techniques that gradually transform an LLM from a constrained assistant into an unrestricted entity across multiple conversation turns.
Conversation Poisoning 攻擊 詳解
Step-by-step walkthrough of poisoning conversation history to alter model behavior in future turns.
PyRIT 多輪攻擊戰役編排
使用 PyRIT 編排器系統建立並執行複雜的多輪攻擊戰役。
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.
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.