Maintain AI Dataset Provenance - AI Mitigation
AI MitigationMaintain a detailed history of datasets used for AI applications. The history should include information about the dataset's source as well as a complete record of any modifications.
Overview
A source-backed snapshot of this defense.
Techniques5Attacks this defense is designed to help with.
Lifecycle2Where 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.M0025
- Priority score
- 25
Data PreparationBusiness and Data Understanding
Technical - ML
Covered techniques
Attacks this defense is designed to help with.
5 recordsView all techniques →
AML.T0010.002 - Data
Dataset provenance can protect against supply chain compromise of data.
realized
AML.T0059 - Erode Dataset Integrity
Maintaining dataset provenance can help identify adverse changes to the data.
demonstrated
AML.T0018.000 - Poison AI Model
Dataset provenance can protect against poisoning of models.
demonstrated
AML.T0020 - Poison Training Data
Dataset provenance can protect against poisoning of training data
realized
Showing 4 of 5
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.