General Susceptibility - Exploitability

From The Foundation for Best Practices in Machine Learning
Technical Best Practices > Security > General Susceptibility - Exploitability

General Susceptibility - Exploitability

Control

Document, assess and control the general Model susceptibility to attack due to exploitable properties of Models, considering (a) overfit or highly sensitivity Models and Model hyperparameters are easier to attack; (b) an over-reliance on gradient methods that make Models more predictable and inspectable; (c) Models may be pushed past their applicability boundaries if input is not validated; and (d) non-random random number generators might be replaced by cryptographically secure random number generators.


Aim

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


Additional Information