Model Exfiltration Susceptibility

From The Foundation for Best Practices in Machine Learning
Technical Best Practices > Security > Model Exfiltration Susceptibility

Model Exfiltration Susceptibility

Control

Document and assess the susceptibility of Models to Exfiltration Attacks with the aim of obtaining a copy, or approximation of, the Model or other Organization intellectual property, through repeated querying of the Model and analysing the obtained results and confidence scores.


Aim

To (a) warrant and control the risk of Model and intellectual property theft; and (b) highlight associated risks that might occur in the Product Lifecycle.


Additional Information