Model Hardening - AI Mitigation
AI MitigationUse techniques to make AI models robust to adversarial inputs such as adversarial training or network distillation.
Overview
A source-backed snapshot of this defense.
Techniques8Attacks 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.M0003
- Priority score
- 40
Data PreparationML Model Engineering
Technical - ML
Covered techniques
Attacks this defense is designed to help with.
8 recordsView all techniques →
AML.T0043.001 - Black-Box Optimization
Hardened models are more robust to adversarial inputs.
demonstrated
AML.T0043.002 - Black-Box Transfer
Hardened models are more robust to adversarial inputs.
demonstrated
AML.T0043 - Craft Adversarial Data
Hardened models are more robust to adversarial inputs.
realized
AML.T0031 - Erode AI Model Integrity
Hardened models are less susceptible to integrity attacks.
realized
Showing 4 of 8
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.