AI Intellectual Property Theft
Sub-technique of AML.T0048 External Harms
Description
Adversaries may exfiltrate AI artifacts to steal intellectual property and cause economic harm to the victim organization.
Proprietary training data is costly to collect and annotate and may be a target for Exfiltration and theft.
AIaaS providers charge for use of their API.
An adversary who has stolen a model via Exfiltration or via Extract AI Model now has unlimited use of that service without paying the owner of the intellectual property.
- ATLAS ID
- AML.T0048.004
- Maturity
- RealizedUsed by real adversaries against AI systems in the wild.
- Platforms
- Predictive AIGenerative AIAgentic AIEnterprise
Mitigations
- AML.M0005Control Access to AI Models and Data at Rest
Access controls can prevent theft of intellectual property.
- AML.M0012Encrypt Sensitive Information
Protect machine learning artifacts with encryption.
- AML.M0017AI Model Distribution Methods
Avoiding the deployment of models to edge devices reduces an adversary's potential access to models or AI artifacts.
Case studies that use it
- AML.CS0005Attack on Machine Translation Services
- AML.CS0018Arbitrary Code Execution with Google Colab
- AML.CS0027Organization Confusion on Hugging Face
- AML.CS0028AI Model Tampering via Supply Chain Attack
- AML.CS0056Model Distillation Campaigns Targeting Anthropic Claude
- AML.CS0058Google Photos AI Model Extraction