# feature-store
標記為「feature-store」的 8 篇文章
Vertex AI 攻擊面
為 Vertex AI 之紅隊方法論：預測端點濫用、自訂訓練安全缺口、特徵儲存投毒、模型監控逃避與管線利用。
特徵倉儲操縱
特徵倉儲(Feast、Tecton、Databricks)的操縱攻擊,包含特徵投毒、新鮮度攻擊與存取控制繞過。
特徵儲存的安全
保護 ML 管線中的特徵儲存,防範投毒與未授權存取。
Feature Store Access Control
Access control strategies for feature stores: feature-level permissions, cross-team data leakage prevention, PII protection in features, service account management, and implementing least-privilege access for ML feature infrastructure.
Feature 投毒 攻擊s
Techniques for poisoning feature store data to manipulate model behavior: direct feature value manipulation, time-travel attacks, online/offline store consistency exploitation, and targeted entity-level feature poisoning.
特徵儲存安全（LLMops 安全）
ML 特徵儲存（Feast、Tecton、Vertex Feature Store）之安全概觀：架構與信任模型、線上與離線儲存中之攻擊面，與為 ML 系統之集中化特徵管理之安全意涵。
Vertex AI 紅隊 導覽
End-to-end walkthrough for red teaming Google Cloud Vertex AI: prediction endpoint testing, 模型 Garden security assessment, Feature Store probing, and Cloud Logging analysis.
Vertex AI 紅隊 導覽 (Platform 導覽)
Complete red team walkthrough for Google Vertex AI: testing prediction endpoints, 模型 Garden assessments, Feature Store probing, and exploiting Vertex AI 代理s and Extensions.