Exfiltration Defence

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

Exfiltration Defence

Control

To reduce susceptibility of Exfiltration Attacks, (a) make Exfiltration Attacks computationally expensive; (b) remove as much as possible information from Model Output; (c) add noise to Model Outputs through techniques such as differential privacy; (d) limit querying possibilities in volume and/or scope; and/or (e) change Model architecture.


Aim

To (a) warrant and control the risk of Exfiltration Attacks; and (b) highlight associated risks that might occur in the Product Lifecycle.


Additional Information