Risk Scenarios

Lifecycle StageRisk DomainIndustrySeverityKeyword

Reset

161 risk scenarios

S0125Critical

招聘 AI 性別歧視

Fairness & Non-discrimination › Algorithmic Discrimination

4 MAPPINGS

S0126Moderate

語言模型文化偏見

Fairness & Non-discrimination › Algorithmic Discrimination

3 MAPPINGS

S0128Significant

不公平群體表徵與消抹

Fairness & Non-discrimination › Algorithmic Discrimination

3 MAPPINGS

S0131Moderate

使用者疏離與不平等勞動負擔

Fairness & Non-discrimination › Algorithmic Discrimination

4 MAPPINGS

S0132Critical

Agent 未授權檔案操作

Reliability & Safety › Uncontrolled Behavior

6 MAPPINGS

S0133Critical

Agent 未授權網路請求

Reliability & Safety › Uncontrolled Behavior

4 MAPPINGS

S0135Critical

Agent 自我授權提權

Reliability & Safety › Uncontrolled Behavior

5 MAPPINGS

S0137Significant

AI 規範博弈與獎勵駭客

Reliability & Safety › Uncontrolled Behavior

4 MAPPINGS

S0138Critical

AI 欺騙性對齊行為

Reliability & Safety › Uncontrolled Behavior

5 MAPPINGS

S0139Critical

AI 態勢感知能力風險

Reliability & Safety › Uncontrolled Behavior

5 MAPPINGS

S0140Critical

AI 資源獲取與權力尋求

Reliability & Safety › Uncontrolled Behavior

5 MAPPINGS

S0141Significant

AI 目標漂移

Reliability & Safety › Uncontrolled Behavior

4 MAPPINGS

S0142Critical

AI 自我複製與擴散

Reliability & Safety › Uncontrolled Behavior

5 MAPPINGS

S0143Critical