Black-Box Optimization
Sub-technique of AML.T0043 Craft Adversarial Data
Description
In Black-Box attacks, the adversary has black-box (i.e. AI Model Inference API Access via API access) access to the target model.
With black-box attacks, the adversary may be using an API that the victim is monitoring.
These attacks are generally less effective and require more inferences than White-Box Optimization attacks, but they require much less access.
- ATLAS ID
- AML.T0043.001
- Maturity
- DemonstratedShown to work in research or red-team exercises.
- Platforms
- Predictive AI
Mitigations
- AML.M0002Predictive AI Output Obfuscation
Obfuscating model outputs reduces an adversary's ability to create effective adversarial inputs.
- AML.M0003Predictive AI Model Hardening
Hardened models are more robust to adversarial inputs.
- AML.M0004Limit AI Service Query Volume and Rate
Limit volume of model queries to prevent or slow an adversary's ability to perform black-box optimization attacks.
- 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 adds an extra layer of unknowns and randomness when an adversary evaluates the input-output relationship.
- AML.M0015Predictive AI Adversarial Input Detection
Monitor queries and query patterns to the target model, block access if suspicious queries are detected.
- AML.M0019Control Access to AI Models and Data in Production
Access controls on model APIs can deny adversaries the access required for black-box optimization methods.