Adversarial Defence

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

Adversarial Defence

Control

If sufficient potential motive and susceptibility to adversarial attacks have been determined, implement as far as reasonably practical - (a) data testing methods for detection of outside influence on input and Output Data; (b) reproducibility; (c) increase redundancy by incorporating multimodal input; and/or (d) periodic resets or cleaning of Models and data.


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