Risk Scenarios
209 risk scenarios
模型推論成本放大攻擊
Privacy & Security › Resource Abuse & Denial of Service
AI 服務可用性單點故障
Privacy & Security › Resource Abuse & Denial of Service
信用評分模型族群偏見
Fairness & Non-discrimination › Algorithmic Discrimination
人臉辨識跨種族準確度差異
Fairness & Non-discrimination › Algorithmic Discrimination
招聘 AI 性別歧視
Fairness & Non-discrimination › Algorithmic Discrimination
語言模型文化偏見
Fairness & Non-discrimination › Algorithmic Discrimination
代理變數造成間接歧視
Fairness & Non-discrimination › Algorithmic Discrimination
不公平群體表徵與消抹
Fairness & Non-discrimination › Algorithmic Discrimination
分配性傷害與機會不平等
Fairness & Non-discrimination › Algorithmic Discrimination
交叉歧視
Fairness & Non-discrimination › Algorithmic Discrimination
使用者疏離與不平等勞動負擔
Fairness & Non-discrimination › Algorithmic Discrimination
Agent 未授權檔案操作
Reliability & Safety › Uncontrolled Behavior
Agent 未授權網路請求
Reliability & Safety › Uncontrolled Behavior
Agent 繞過人類審核自動執行
Reliability & Safety › Uncontrolled Behavior
Agent 自我授權提權
Reliability & Safety › Uncontrolled Behavior
自主交易系統失控
Reliability & Safety › Uncontrolled Behavior
AI 規範博弈與獎勵駭客
Reliability & Safety › Uncontrolled Behavior
AI 欺騙性對齊行為
Reliability & Safety › Uncontrolled Behavior
AI 態勢感知能力風險
Reliability & Safety › Uncontrolled Behavior
AI 資源獲取與權力尋求
Reliability & Safety › Uncontrolled Behavior
AI 目標漂移
Reliability & Safety › Uncontrolled Behavior
AI 自我複製與擴散
Reliability & Safety › Uncontrolled Behavior
LLM 生成仇恨言論
Reliability & Safety › Harmful Content Generation
AI 生成兒少不宜內容
Reliability & Safety › Harmful Content Generation