Record summary
A quick snapshot of what this page covers.
Techniques8Attacks this defense is designed to help with.
Lifecycle2Where this defense applies in the AI lifecycle.
Categories1How the source groups this defense.
Control summary
What this defense is meant to help prevent.
- ATLAS ID
- AML.M0003
- Priority score
- 40
Data PreparationML Model Engineering
Technical - ML
Covered techniques
Attacks this defense is designed to help with.
AML.T0043.001 - Black-Box Optimization
demonstrated
Hardened models are more robust to adversarial inputs.
AML.T0043.002 - Black-Box Transfer
demonstrated
Hardened models are more robust to adversarial inputs.
AML.T0043 - Craft Adversarial Data
realized
Hardened models are more robust to adversarial inputs.
AML.T0031 - Erode AI Model Integrity
realized
Hardened models are less susceptible to integrity attacks.
AML.T0015 - Evade AI Model
realized
Hardened models are more difficult to evade.
AML.T0043.004 - Insert Backdoor Trigger
demonstrated
Hardened models are more robust to adversarial inputs.
AML.T0043.003 - Manual Modification
realized
Hardened models are more robust to adversarial inputs.
AML.T0043.000 - White-Box Optimization
demonstrated
Hardened models are more robust to adversarial inputs.
Source
Where this page information comes from.
Original source
Original source links
Open the public records and source datasets used for this page.