MITRE ATLAS Poison AI Model (AML.T0018.000) - Adversarial Poison AI Model threat to AI systems

What MITRE ATLAS Poison AI Model (AML.T0018.000) - Adversarial Poison AI Model threat to AI systems requires

This node addresses MITRE ATLAS technique AML.T0018.000 (Poison AI Model). Adversaries may manipulate an AI model's weights to change it's behavior or performance, resulting in a poisoned model. Adversaries may poison a model by directly manipulating its weights, training the model on poisoned data, further fine-tuning the model, or otherwise interfering with its training process. The change in behavior of poisoned models may be limited to targeted categories in predictive AI models, or targeted topics, concepts, or facts in generative AI models, or aim for a general performance degradation. 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.T0018. ATLAS-mapped mitigations: AML.M0005 Control Access to AI Models and Data at Rest, AML.M0007 Sanitize Training Data, AML.M0008 Validate AI Model, AML.M0013 Code Signing, AML.M0025 Maintain AI Dataset Provenance.

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: 786cedb7b70df75e1dd9bc0d83ed95d578b99567e618aa5a106f97a1690faee1

Primary Citations — 10 traced to source

• MITRE ATLAS - Poison AI Model (AML.T0018.000), https://raw.githubusercontent.com/mitre-atlas/atlas-data/main/dist/ATLAS.yaml#AML.T0018.000, AML.T0018.000 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

+ 8 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-poison-ai-model.json — 6-field metadata
• Vault (full node): /api/v1/vault/nodes/mitre-atlas-poison-ai-model.json — full 13-key payload, $0.01 USDC (L402/Skyfire/Direct Base)
• Canonical URL: https://bidda.com/intelligence/mitre-atlas-poison-ai-model
• Back to registry: Browse all 10,099 compliance nodes