Passive AI Output Obfuscation - AI Mitigation
AI MitigationDecreasing the fidelity of model outputs provided to the end user can reduce an adversary's ability to extract information about the model and optimize attacks for the model.
Overview
A source-backed snapshot of this defense.
Safeguard details
Where this defense applies and how the source classifies it.
- ATLAS ID
- AML.M0002
- Priority score
- 55
Covered techniques
Attacks this defense is designed to help with.
AML.T0043.001 - Black-Box Optimization
Obfuscating model outputs reduces an adversary's ability to create effective adversarial inputs.
AML.T0043 - Craft Adversarial Data
Obfuscating model outputs reduces an adversary's ability to generate effective adversarial data.
AML.T0005 - Create Proxy AI Model
Obfuscating model outputs can reduce an adversary's ability to produce an accurate proxy model.
AML.T0014 - Discover AI Model Family
Suggested approaches:
- Restrict the number of results shown
- Limit specificity of output class ontology
- Use randomized smoothing techniques
- Reduce the precision of numerical outputs
Showing 4 of 10
Source evidence
Original public records and references for this page.
Original source
Original source links
Open the public records and source datasets used for this page.