Black-Box Transfer
Sub-technique of AML.T0043 Craft Adversarial Data
Description
In Black-Box Transfer attacks, the adversary uses one or more proxy models (trained via Create Proxy AI Model or Train Proxy via Replication) they have full access to and are representative of the target model.
The adversary uses White-Box Optimization on the proxy models to generate adversarial examples.
If the set of proxy models are close enough to the target model, the adversarial example should generalize from one to another.
This means that an attack that works for the proxy models will likely then work for the target model.
If the adversary has AI Model Inference API Access, they may use Verify Attack to confirm the attack is working and incorporate that information into their training process.
- ATLAS ID
- AML.T0043.002
- 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.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.