Ensemble Methods

Ensemble methods are when multiple AI models are used in conjunction to achieve better results. It has been recommended to use ensemble models to perform inference as it increases its adversarial robustness. Some attacks may effectively evade one model or model family, however ineffective against others. Using multiple models in conjunction with each other allow model predictions to be verified through consensus, verifying each other’s model outputs.

​

Explanation

​

How it works

​

How to implement