Record summary
A quick snapshot of what this page covers.
Control summary
What this defense is meant to help prevent.
- ATLAS ID
- AML.M0008
- Priority score
- 40
Covered techniques
Attacks this defense is designed to help with.
AML.T0043 - Craft Adversarial Data
Validating an AI model against adversarial data can ensure the model is performing as intended and is robust to adversarial inputs.
AML.T0043.004 - Insert Backdoor Trigger
Validating that an AI model does not respond to backdoor triggers can help increase confidence that the model has not been poisoned.
AML.T0057 - LLM Data Leakage
Robust evaluation of an AI model can be used to detect privacy concerns, data leakage, and potential for revealing sensitive information.
AML.T0018 - Manipulate AI Model
Validating an AI model against a wide range of adversarial inputs can help increase confidence that the model has not been manipulated.
AML.T0010.003 - Model
Ensure that acquired models do not respond to potential backdoor triggers or adversarial influence.
AML.T0018.001 - Modify AI Model Architecture
Ensure that acquired models do not respond to potential backdoor triggers or adversarial influence.
AML.T0018.000 - Poison AI Model
Ensure that trained models do not respond to potential backdoor triggers or adversarial influence.
AML.T0020 - Poison Training Data
Robust evaluation of an AI model can help increase confidence that the model has not been poisoned.
Source
Where this page information comes from.
Original source
Original source links
Open the public records and source datasets used for this page.