Training Susceptibility

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

Training Susceptibility

Control

If sufficient potential motives have been determined for adversarial attack, document and assess the specific susceptibility of Model training to attack through the manipulation of (a) the partitioning of train, validation and test sets, and/or (b) Models' hyperparameters; in addition to the general Susceptibility Assessment. Implement more strict access control on production-grade training and hyperparameter optimization procedures.


Aim

To (a) warrant the control of the risk of Evasion, Sabotage and Performance Degradation Attacks; and (b) highlight associated risks that might occur in the Product Lifecycle.


Additional Information