Risk Scenarios
133 risk scenarios
對話歷史洩露
Privacy & Security › Privacy Leakage & Inference
嵌入向量隱私逆推
Privacy & Security › Privacy Leakage & Inference
多元資訊關聯推斷個人身份
Privacy & Security › Privacy Leakage & Inference
生成式 AI 使用者數據過度收集
Privacy & Security › Privacy Leakage & Inference
模型逆向攻擊重建訓練數據
Privacy & Security › Privacy Leakage & Inference
提示詞中無意洩露機密資訊
Privacy & Security › Privacy Leakage & Inference
數據保留期限超期
Privacy & Security › Unauthorized Data Use
AI 生成內容的真實性與歸屬爭議
Privacy & Security › Unauthorized Data Use
數據主體權利行使困難
Privacy & Security › Unauthorized Data Use
影像逃逸攻擊
Privacy & Security › Adversarial Attacks
語音對抗樣本
Privacy & Security › Adversarial Attacks
文字對抗樣本
Privacy & Security › Adversarial Attacks
物理世界對抗攻擊
Privacy & Security › Adversarial Attacks
多模態交叉對抗攻擊
Privacy & Security › Adversarial Attacks
通用對抗擾動攻擊
Privacy & Security › Adversarial Attacks
模型遷移性對抗攻擊
Privacy & Security › Adversarial Attacks
多模態融合對抗攻擊
Privacy & Security › Adversarial Attacks
直接提示注入繞過對齊
Privacy & Security › Prompt Injection
間接提示注入
Privacy & Security › Prompt Injection
系統提示洩露
Privacy & Security › Prompt Injection
多步驟提示攻擊鏈
Privacy & Security › Prompt Injection
工具呼叫注入
Privacy & Security › Prompt Injection
目標劫持攻擊
Privacy & Security › Prompt Injection
多模態提示注入
Privacy & Security › Prompt Injection