Encrypt Sensitive Information - AI Mitigation
AI MitigationEncrypt sensitive data such as AI models to protect against adversaries attempting to access sensitive data.
Overview
A source-backed snapshot of this defense.
Techniques4Attacks this defense is designed to help with.
Lifecycle3Where this defense applies in the AI lifecycle.
Categories1How the source groups this defense.
Safeguard details
Where this defense applies and how the source classifies it.
- ATLAS ID
- AML.M0012
- ATT&CK external ID
- M1041
- Priority score
- 20
Data PreparationML Model EngineeringDeployment
Technical - Cyber
Covered techniques
Attacks this defense is designed to help with.
4 recordsView all techniques →
AML.T0035 - AI Artifact Collection
Protect machine learning artifacts with encryption.
realized
AML.T0048.004 - AI Intellectual Property Theft
Protect machine learning artifacts with encryption.
realized
AML.T0007 - Discover AI Artifacts
Encrypting AI artifacts can protect against adversary attempts to discover sensitive information.
demonstrated
AML.T0063 - Discover AI Model Outputs
Encrypting model outputs can prevent adversaries from discovering sensitive information about the AI-enabled system or its operations.
demonstrated
Source evidence
Original public records and references for this page.
Original source
Original source links
Open the public records and source datasets used for this page.
