White-Box Optimization
Sub-technique of AML.T0043 Craft Adversarial Data
Description
In White-Box Optimization, the adversary has full access to the target model and optimizes the adversarial example directly.
Adversarial examples trained in this manner are most effective against the target model.
- ATLAS ID
- AML.T0043.000
- Maturity
- DemonstratedShown to work in research or red-team exercises.
- Platforms
- Predictive AI
Mitigations
- AML.M0003Predictive AI Model Hardening
Hardened models are more robust to adversarial inputs.
- AML.M0005Control Access to AI Models and Data at Rest
Access controls can reduce unnecessary access to AI models and prevent an adversary from achieving white-box access.
- AML.M0006Predictive AI Ensembles
Using an ensemble of models increases the difficulty of crafting effective adversarial data and improves overall robustness.
- AML.M0010Predictive AI Input Restoration
Input restoration can help remediate adversarial inputs.
- AML.M0015Predictive AI Adversarial Input Detection
Incorporate adversarial input detection to block malicious inputs at inference time.
- AML.M0017AI Model Distribution Methods
With full access to the model, an adversary could perform white-box attacks.