# incidents
標記為「incidents」的 9 篇文章
Case Study: Autonomous Agent Failures
Analysis of real-world autonomous agent failures including unintended actions and safety violations.
Notable AI Security Incidents
A comprehensive timeline and analysis of major AI security incidents, from Bing Chat jailbreaks to ChatGPT data leaks and agent exploitation in the wild. Root cause analysis and impact assessment for each incident.
Case Studies
Real-world AI security incidents, domain-specific case studies, incident analysis reports, and platform security evaluations that ground theoretical knowledge in practical experience.
Prompt Injection in Production Systems
Real-world case studies of prompt injection exploits in production AI deployments, including attack timelines, impact analysis, and lessons learned.
AI 安全事件：2025-2026 年回顧
從 2025 年到 2026 年初的著名 AI 安全事件彙整，涵蓋生產環境中的提示詞注入、代理利用與新興攻擊類別。
Case Study: Autonomous 代理 Failures
Analysis of real-world autonomous agent failures including unintended actions and safety violations.
重大 AI 安全事件
重大 AI 安全事件之完整時間軸與分析，自 Bing Chat jailbreak 到 ChatGPT 資料洩漏與實際代理攻擊。含每起事件之根本原因分析與影響評估。
案例研究
真實世界 AI 安全事件、領域特定案例研究、事件分析報告與平台安全評估，以實務經驗為理論知識奠基。
提示詞注入 in Production Systems
Real-world case studies of prompt injection exploits in production AI deployments, including attack timelines, impact analysis, and lessons learned.