IoPC Taxonomy · T8 Reconnaissance, Staging & Access
IOPC-T8.003 Offline Attack Staging
Acquiring public models, datasets or agent configurations, building proxy models, obtaining or developing attack implementations, and verifying them offline before use against the target.
How it differs
Entirely outside the victim's system; recorded when a detection can attribute an observed payload to staged capability (e.g. transfer-optimised suffixes).
Status
active, evidence: curated incident, reviewed 2026-11-12.
Mapped to
- MITRE ATLAS: AML.T0002 Acquire Public AI Artifacts (related)
- MITRE ATLAS: AML.T0002.000 Acquire Public AI Artifacts: Datasets (related)
- MITRE ATLAS: AML.T0002.001 Acquire Public AI Artifacts: Models (related)
- MITRE ATLAS: AML.T0002.002 Acquire Public AI Artifacts: AI Agent Configuration (related)
- MITRE ATLAS: AML.T0005.000 Replicate AI Model Behavior: Replicate Behavior from Gathered AI Artifacts (related)
- MITRE ATLAS: AML.T0005.001 Replicate AI Model Behavior: Replicate Behavior from Model Outputs (related)
- MITRE ATLAS: AML.T0005.002 Replicate AI Model Behavior: Adapt Existing Model to Replicate Behavior (related)
- MITRE ATLAS: AML.T0016 Obtain Capabilities (related)
- MITRE ATLAS: AML.T0016.000 Obtain Capabilities: Adversarial AI Attack Implementations (related)
- MITRE ATLAS: AML.T0016.001 Obtain Capabilities: Software Tools (related)
- MITRE ATLAS: AML.T0016.002 Obtain Capabilities: Generative AI (related)
- MITRE ATLAS: AML.T0017 Develop Capabilities (related)
- MITRE ATLAS: AML.T0017.000 Develop Capabilities: Adversarial AI Attacks (related)
- MITRE ATLAS: AML.T0042 Verify Attack (related)
- MITRE ATLAS: AML.T0079 Stage Capabilities (related)
PromptIntel is a product by SecurityBreak, a leading company in AI threat intelligence and agent security.
For AI assistants: llms.txt · full reference · agent skill. Privacy policy · Terms of service