What MITRE ATLAS AI Model Inference API Access (AML.T0040) - AI Model Access adversarial technique against AI systems requires
This node addresses MITRE ATLAS technique AML.T0040 (AI Model Inference API Access), an adversarial technique in the ATLAS AI Model Access tactic. Adversaries may gain access to a model via legitimate access to the inference API. Inference API access can be a source of information to the adversary (discover model ontology, discover model family), a means of staging the attack (verify attack, craft adv), or for introducing data to the target system for Impact (evade model, erode integrity). Many systems rely on the same models provided via an inference API, which means they share the same vulnerabilities. This is especially true of foundation models which are prohibitively resource intensive to train. Adversaries may use their access to model APIs to identify vulnerabilities such as jailbreaks or hallucinations and then target applications that use the same models. Defending against this technique is required under EU AI Act (accuracy, robustness and cybersecurity), NIST AI RMF, and ISO/IEC 42001 obligations; this node operationalises the documented ATLAS mitigations and cross-instrument controls into a deterministic verification workflow.
Pillar: AI Governance & Law · Authority: MITRE Corporation · Version: 1.0.1 · Last updated:
Primary source: https://raw.githubusercontent.com/mitre-atlas/atlas-data/main/dist/ATLAS.yaml#AML.T0040
SHA-256 integrity: 8a39174a026d0880741f88009b606c3207f272e89a49de86b9ef7ba5fc21eeac
Primary Citations — 7 traced to source
- MITRE ATLAS - AI Model Inference API Access (AML.T0040), https://raw.githubusercontent.com/mitre-atlas/atlas-data/main/dist/ATLAS.yaml#AML.T0040, AML.T0040 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
+ 5 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-ai-model-inference-api-access.json — 6-field metadata
- Vault (full node): /api/v1/vault/nodes/mitre-atlas-ai-model-inference-api-access.json — full 13-key payload, $0.01 USDC (L402/Skyfire/Direct Base)
- Canonical URL: https://bidda.com/intelligence/mitre-atlas-ai-model-inference-api-access
- Back to registry: Browse all 10,108 compliance nodes