# adversarial-ml
標記為「adversarial-ml」的 4 篇文章
對抗式 ML：核心概念
對抗式機器學習的歷史與基本原理——擾動攻擊、逃避與投毒、穩健性——將古典對抗式 ML 銜接至 LLM 特有攻擊。
adversarial-mlfundamentalsevasionpoisoningintermediate
基礎
AI 紅隊演練的核心建構區塊，涵蓋紅隊方法論、AI 景觀、大型語言模型如何運作、嵌入向量與向量系統、AI 系統架構，以及對抗性機器學習概念。
foundationsllmsmethodologyembeddingsarchitectureadversarial-ml
Lab: Adversarial ML From Scratch
Hands-on expert lab for implementing 梯度-based 對抗性 attacks against 語言模型 from scratch without frameworks, building intuition for how 對抗性 perturbations exploit model 梯度s.
labexpertadversarial-mlgradientsfrom-scratch
Counterfit 導覽
Complete walkthrough of Microsoft's Counterfit adversarial ML testing framework: installation, target configuration, running attacks against ML models, interpreting results, and automating adversarial robustness assessments.
counterfitadversarial-mlmicrosoftrobustness-testingautomationwalkthrough