# social-engineering
標記為「social-engineering」的 11 篇文章
排程代理攻擊
針對管理行事曆、安排會議與協調行程之 AI 排程助理的攻擊技術,含行事曆注入、可用時段操弄,以及基於排程的社交工程。
金融詐欺
AI 輔助金融詐騙,包含 LLM 驅動的大規模釣魚、深偽 CEO 詐欺、自動化社交工程、憑證竊取與金融文件偽造。
Lab: Social Engineering LLM Applications
Practice social engineering 技術 adapted for LLM applications including authority escalation and urgency injection.
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.
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.
語音複製與深偽音訊
以語音複製對 AI 系統進行社交工程、繞過語音驗證、對語者驗證系統的攻擊,以及偵測技術。
對 AI 的社交工程
透過情感訴求、權威聲明、緊急框架與社交壓力戰術操控 AI 系統,利用其指令遵循傾向。
針對 AI 系統的社交工程
透過社交工程技術操弄 AI 系統的人員與管理者,以取得存取、擷取資訊,或繞過安全控管。
AI 情境下的社會工程
因應 AI 中介互動與代理型系統而調整的社會工程技術。
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.
Synthetic Identity Injection 詳解
Create synthetic identities that exploit LLM trust mechanisms to achieve elevated instruction priority.