MITRE ATLAS Use Pre-Trained Model (AML.T0005.002) - Adversarial Use Pre-Trained Model threat to AI systems

What MITRE ATLAS Use Pre-Trained Model (AML.T0005.002) - Adversarial Use Pre-Trained Model threat to AI systems requires

This node addresses MITRE ATLAS technique AML.T0005.002 (Use Pre-Trained Model). Adversaries may use an off-the-shelf pre-trained model as a proxy for the victim model to aid in staging the attack. Defending against this technique is required under EU AI Act, NIST AI RMF, and ISO/IEC 42001 obligations; this node operationalises the documented ATLAS mitigations and cross-instrument controls into a deterministic verification workflow. Sub-technique of ATLAS AML.T0005. ATLAS-mapped mitigations: AML.M0000 Limit Public Release of Information.

Pillar: AI Governance & Law · Authority: MITRE Corporation · Version: 1.0.1 · Last updated: 2026-07-22

Primary source: https://raw.githubusercontent.com/mitre-atlas/atlas-data/main/dist/ATLAS.yaml

SHA-256 integrity: 14ca7b2b354129c59ebf0ade61a1d8d03567b7b2627000d32b87e4d871fdaeb8

Primary Citations — 6 traced to source

• MITRE ATLAS - Use Pre-Trained Model (AML.T0005.002), https://raw.githubusercontent.com/mitre-atlas/atlas-data/main/dist/ATLAS.yaml#AML.T0005.002, AML.T0005.002 technique entry, 2026
• EU AI Act - Regulation (EU) 2024/1689 on Artificial Intelligence, https://eur-lex.europa.eu/legal-content/EN/TXT/?uri=CELEX:32024R1689, Article 15 (Accuracy, Robustness, Cybersecurity), 2024

+ 4 more citations (full bibliography, deterministic workflow, actionable schema and crosswalks) included in the vault unlock — $0.01 via Skyfire / L402 / Direct Base USDC.

Access

• Discovery (free): /api/v1/nodes/mitre-atlas-use-pre-trained-model.json — 6-field metadata
• Vault (full node): /api/v1/vault/nodes/mitre-atlas-use-pre-trained-model.json — full 13-key payload, $0.01 USDC (L402/Skyfire/Direct Base)
• Canonical URL: https://bidda.com/intelligence/mitre-atlas-use-pre-trained-model
• Back to registry: Browse all 10,108 compliance nodes