Resource Development (13 techniques)
MITRE ATLAS tactic
The adversary is trying to establish resources they can use to support operations. Resource Development consists of techniques that involve adversaries creating, purchasing, or compromising/stealing resources that can be used to support targeting. Such resources include AI artifacts, infrastructure, accounts, or capabilities. These resources can be leveraged by the adversary to aid in other phases of the adversary lifecycle, such as [AI Attack Staging](/tactics/AML.TA0001).
Techniques
- AML.T0002 — Acquire Public AI Artifacts Maturity: realized
- AML.T0008 — Acquire Infrastructure Maturity: realized
- AML.T0016 — Obtain Capabilities Maturity: realized
- AML.T0017 — Develop Capabilities Maturity: realized
- AML.T0019 — Publish Poisoned Datasets Maturity: demonstrated
- AML.T0020 — Poison Training Data Maturity: realized
- AML.T0021 — Establish Accounts Maturity: realized
- AML.T0058 — Publish Poisoned Models Maturity: realized
- AML.T0060 — Publish Hallucinated Entities Maturity: demonstrated
- AML.T0065 — LLM Prompt Crafting Maturity: realized
- AML.T0066 — Retrieval Content Crafting Maturity: demonstrated
- AML.T0079 — Stage Capabilities Maturity: demonstrated
- AML.T0104 — Publish Poisoned AI Agent Tool Maturity: realized
AI red teaming training, taught by practitioners.
Hands-on courses on adversarial AI, prompt injection, and AI security operations.
View AI Security Courses