AML.T0044

Full AI Model Access

Adversaries may gain full "white-box" access to an AI model. This means the adversary has complete knowledge of the model architecture, its parameters, and class ontology. They may exfiltrate the model to [Craft Adversarial Data](/techniques/AML.T0043) and [Verify Attack](/techniques/AML.T0042) in an offline where it is hard to detect their behavior.

7 CVEs mapped View on MITRE ATLAS →

Severity	CVE	Headline	Package	CVSS
CRITICAL	CVE-2025-63389	ollama: Missing Auth allows unauthenticated access	ollama	9.8
HIGH	CVE-2026-2033	mlflow: Path Traversal enables file access	mlflow	8.1
HIGH	CVE-2025-30165	vLLM: pickle RCE in multi-node inference deployments	vllm	8.0
HIGH	CVE-2021-37659	TensorFlow: heap OOB in cwise ops enables local RCE	tensorflow	7.8
HIGH	CVE-2021-41201	TensorFlow: uninitialized var in Einsum allows local RCE	tensorflow	7.8
MEDIUM	CVE-2025-2998	PyTorch: memory corruption in RNN pad_packed_sequence	pytorch	5.3
MEDIUM	CVE-2020-15211	TensorFlow Lite: heap OOB RW via flatbuffer tensor index	tensorflow	4.8