这是一门专注于 AI 与机器学习系统安全防御的实战课程。课程以行业权威的 MITRE ATLAS™（针对人工智能系统的对抗威胁景观）框架为核心，借鉴红队实战观测经验，带你建立一套覆盖机器学习全生命周期的威胁建模与防御体系。你将不再抽象地研究漏洞，而是学会像真实攻击者一样思考，从而精准保护企业的生成式 AI 与传统 ML 流水线。
Published 6/2026
Created by NEXUS ACADEMY
MP4 | Video: h264, 1920×1080 | Audio: AAC, 44.1 KHz, 2 Ch
Level: All Levels | Genre: eLearning | Language: English | Duration: 31 Lectures ( 3h 23m ) | Size: 1.4 GB
Threat-model and defend your AI and ML systems against adversarial attacks using the MITRE ATLAS framework
What you’ll learn
⚡ Map adversary tactics and techniques against AI systems using the MITRE ATLAS matrix across the ML lifecycle
⚡ Threat-model your own machine learning and generative-AI pipelines and prioritize risks using ATLAS case studies
⚡ Understand core adversarial ML attacks: evasion, data poisoning and backdoors, model extraction, inversion, and membership inference
⚡ Apply ATLAS mitigations such as adversarial training, model hardening, access limits, and ML supply-chain defenses
⚡ Run an ATLAS-based threat modeling workshop and align it with the NIST AI RMF, MITRE D3FEND, and AI governance
Requirements
❗ Basic familiarity with machine learning concepts or general security fundamentals — deep expertise in either is not required
❗ A computer able to run Python and local or sandboxed ML models for the hands-on labs
Description
“This course contains the use of artificial intelligence.”
MITRE ATLAS (Adversarial Threat Landscape for Artificial-Intelligence Systems) is a knowledge base of real-world adversary tactics, techniques, and case studies targeting machine learning and AI systems, modeled on MITRE ATT&CK and built from red-team observations. This course teaches you to use ATLAS to threat-model your own AI systems, not just to study attacks in the abstract.
You will walk the full ATLAS matrix tactic by tactic, from Reconnaissance and Resource Development through AI-specific tactics like ML Model Access and ML Attack Staging, all the way to Collection, Exfiltration, and Impact, and map a real AI attack onto it. Then you will get hands-on with the core adversarial ML attack classes aligned to the NIST AI 100-2 taxonomy: evasion (adversarial examples at inference), data poisoning and backdoors, model extraction and stealing, model inversion, and membership inference. A focused section covers how ATLAS now catalogs generative-AI and LLM threats, including prompt injection, jailbreaks, meta prompt extraction, and plugin and supply-chain compromise.
Crucially, every attack is paired with a defense. You will map ATLAS mitigations to techniques, apply adversarial training and model hardening, protect data and privacy, limit model access, and secure your ML supply chain. Finally, you will learn to run an ATLAS-based threat modeling workshop, prioritize risks with the ATLAS Navigator and case studies, build an AI red-teaming practice, and align your program with the NIST AI Risk Management Framework, MITRE D3FEND, and modern AI governance. All labs run on local or sandboxed models with your own data, never against live third-party AI services, and stay vendor-neutral.
Who this course is for
⭐ ML and AI engineers and data scientists who want to defend the models and pipelines they build
⭐ Security engineers, blue teamers, and AI risk professionals who need to threat-model AI systems with a shared framework
Password/解压密码www.tbtos.com
转载请注明：0daytown » MITRE ATLAS: Securing AI Systems Against Adversarial Attacks